INDEX

Explanations

phrases related to special events or noteworthy entities

oai_token-act-pair · gpt-3.5-turbo

key terms related to noteworthy events and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Frames

-0.79

assies

-0.78

 olds

-0.72

inations

-0.71

$.

-0.69

casts

-0.69

agements

-0.68

ernels

-0.67

pees

-0.67

rals

-0.66

POSITIVE LOGITS

 spokesperson

1.07

 researcher

0.97

 spokeswoman

0.95

ccording

0.93

 spokesman

0.92

 commenter

0.83

 disclaimer

0.79

 study

0.79

 reader

0.79

 emerges

0.79

Activations Density 0.361%

phrases related to special events or noteworthy entities

key terms related to noteworthy events and reports

No Comments

No Known Activations