INDEX

Explanations

quotes within text

oai_token-act-pair · gpt-3.5-turbo

quoted speech or dialogue segments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 favor

-0.81

 sway

-0.81

 favored

-0.78

 periodic

-0.78

 adjud

-0.76

 dispar

-0.75

 unborn

-0.74

 parting

-0.74

 meta

-0.74

rul

-0.72

POSITIVE LOGITS

They

1.39

We

1.36

It

1.35

Especially

1.33

Because

1.33

Everybody

1.32

Whereas

1.32

Nobody

1.32

Sometimes

1.31

Activations Density 0.081%

quotes within text

quoted speech or dialogue segments

No Comments

No Known Activations