INDEX

Explanations

phrases indicating implications or conclusions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating inference or conclusions drawn from evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uss

-0.73

kees

-0.65

 toured

-0.63

ird

-0.63

queue

-0.62

 presided

-0.62

hari

-0.60

 hyster

-0.60

oqu

-0.58

 wrest

-0.58

POSITIVE LOGITS

Flag

0.79

geries

0.65

 indications

0.65

ression

0.63

evidence

0.63

Leaks

0.63

rists

0.61

 suspicions

0.61

 validity

0.61

ably

0.61

Activations Density 0.165%

phrases indicating implications or conclusions

phrases indicating inference or conclusions drawn from evidence

No Comments

No Known Activations