INDEX

Explanations

names or instances of someone being inducted into a specific group or organization

oai_token-act-pair · gpt-3.5-turbo

the term "induct" and its variations related to inclusion or recognition in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shutterstock

-0.66

OPS

-0.66

 Alic

-0.66

 nerv

-0.65

 Eden

-0.64

 Weed

-0.62

 Indies

-0.62

 Codex

-0.62

 Coastal

-0.61

 Hedge

-0.61

POSITIVE LOGITS

 induct

1.25

untarily

1.15

 induction

0.91

iple

0.88

interstitial

0.87

uting

0.86

ãĤĭ

0.84

Bone

0.79

uct

0.79

eligible

0.78

Activations Density 0.026%

names or instances of someone being inducted into a specific group or organization

the term "induct" and its variations related to inclusion or recognition in various contexts

No Comments

No Known Activations