INDEX

Explanations

trigger words related to news headlines or articles, potentially focusing on actions or events involving notable individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 nowadays

-0.70

 tomorrow

-0.69

 sooner

-0.68

 later

-0.65

 strives

-0.64

 faiths

-0.62

Anyway

-0.61

 tends

-0.61

 denies

-0.61

ago

-0.61

POSITIVE LOGITS

perty

0.75

 again

0.72

igslist

0.63

Reviewer

0.60

itled

0.59

 announcing

0.58

FTWARE

0.56

 commemorate

0.56

 formally

0.56

 another

0.55

Activations Density 0.845%

trigger words related to news headlines or articles, potentially focusing on actions or events involving notable individuals or organizations

No Comments

No Known Activations