INDEX

Explanations

mentions of objects or concepts related to a "chain"

oai_token-act-pair · gpt-3.5-turbo

references to "chain" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

sburg

-0.90

gdala

-0.79

racuse

-0.78

sburgh

-0.78

 "$:/

-0.78

orescent

-0.78

tk

-0.77

matter

-0.77

odder

-0.76

tical

-0.72

POSITIVE LOGITS

chain

0.97

 chain

0.96

mail

0.89

Chain

0.85

loader

0.83

alysis

0.82

wal

0.81

worm

0.78

 chains

0.78

cloth

0.75

Activations Density 0.013%

mentions of objects or concepts related to a "chain"

references to "chain" in various contexts

No Comments

No Known Activations