INDEX

Explanations

sentences related to events or actions involving people

oai_token-act-pair · gpt-3.5-turbo

comma-separated lists of items or descriptors within a context

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

yt

-0.73

EngineDebug

-0.69

Ĭ

-0.67

role

-0.66

Throw

-0.64

KNOWN

-0.63

ongevity

-0.63

Shut

-0.62

ibo

-0.62

hed

-0.62

POSITIVE LOGITS

 however

0.83

 Goldstein

0.75

 meanwhile

0.73

 researchers

0.69

 analysts

0.67

 moreover

0.67

Bie

0.65

 clinicians

0.64

 Commissioner

0.63

 doctors

0.63

Activations Density 0.370%

sentences related to events or actions involving people

comma-separated lists of items or descriptors within a context

No Comments

No Known Activations