INDEX

Explanations

specific items or entities in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence or availability of items or information

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

stroke

-0.74

assisted

-0.67

istry

-0.63

commit

-0.63

vision

-0.62

awar

-0.62

cancer

-0.61

forming

-0.61

jab

-0.60

wake

-0.60

POSITIVE LOGITS

 plenty

0.91

èĢħ

0.83

enance

0.78

¶æ

0.73

abilia

0.72

 traces

0.72

 ample

0.72

 fewer

0.70

ãĤ¤ãĥĪ

0.70

omething

0.69

Activations Density 0.057%

specific items or entities in various contexts

phrases indicating the presence or availability of items or information

No Comments

No Known Activations