INDEX

Explanations

phrases related to lifting objects or mechanisms

oai_token-act-pair · gpt-3.5-turbo

terms related to lifting and elevating objects

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

ually

-0.75

Dialogue

-0.69

clair

-0.69

stown

-0.67

icol

-0.67

 Palin

-0.67

ãģ®éŃĶ

-0.66

tex

-0.65

lished

-0.65

NULL

-0.64

POSITIVE LOGITS

lift

1.29

 lift

1.15

ĸļ

1.10

 lifting

1.00

lifting

0.97

 Lift

0.94

 lifts

0.90

ifter

0.86

 weights

0.84

weight

0.81

Activations Density 0.027%

phrases related to lifting objects or mechanisms

terms related to lifting and elevating objects

No Comments

No Known Activations