INDEX

Explanations

questions posed in a formal or informative context

oai_token-act-pair · gpt-3.5-turbo

references to questions or inquiries

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

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

 pocket

-0.72

utton

-0.70

rawdownloadcloneembedreportprint

-0.70

oche

-0.68

seless

-0.66

éĹĺ

-0.66

ãĥģ

-0.65

itime

-0.64

heartedly

-0.63

olesc

-0.63

POSITIVE LOGITS

 Explain

1.44

 Were

1.14

 Desc

1.07

 Tell

1.06

Did

1.00

How

0.99

Did

0.98

 Lastly

0.97

Tell

0.97

Are

0.96

Activations Density 0.250%

questions posed in a formal or informative context

references to questions or inquiries

No Comments

No Known Activations