INDEX

Explanations

adjectives or nouns indicating importance, significance, or centrality

oai_token-act-pair · gpt-3.5-turbo

words that emphasize significance or importance 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

claimer

-0.77

ften

-0.75

mma

-0.74

iphate

-0.73

erie

-0.73

ansion

-0.72

idae

-0.71

 Canaver

-0.70

ipal

-0.69

amera

-0.68

POSITIVE LOGITS

 situations

0.93

 parts

0.92

 areas

0.92

 portions

0.92

 sectors

0.92

 segments

0.92

 levels

0.92

 groups

0.90

 amounts

0.90

 occasions

0.90

Activations Density 0.443%

adjectives or nouns indicating importance, significance, or centrality

words that emphasize significance or importance in various contexts

No Comments

No Known Activations