INDEX

Explanations

words related to essential or core aspects

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "essence."

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

airs

-0.73

orders

-0.70

 mouths

-0.69

riages

-0.68

 Chim

-0.68

vernment

-0.66

 chairs

-0.64

 Nights

-0.63

few

-0.62

 sidewalks

-0.62

POSITIVE LOGITS

 essence

1.03

uality

0.86

atsu

0.84

ELF

0.77

IME

0.75

uary

0.73

ful

0.72

ItemTracker

0.69

estro

0.68

iary

0.68

Activations Density 0.013%

words related to essential or core aspects

references to the concept of "essence."

No Comments

No Known Activations