INDEX

Explanations

phrases related to explanation or reasoning

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate attribution or parts of a whole

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soever

-0.85

rams

-0.79

ancies

-0.75

ittal

-0.75

 teasp

-0.74

ãģ®éŃĶ

-0.72

estyles

-0.70

oons

-0.69

ãĤ¼ãĤ¦ãĤ¹

-0.68

erion

-0.66

POSITIVE LOGITS

why

1.22

 what

0.92

 reason

0.89

 explaining

0.83

why

0.79

 being

0.79

WHY

0.78

me

0.77

 understanding

0.76

 overcoming

0.75

Activations Density 0.076%

phrases related to explanation or reasoning

phrases that indicate attribution or parts of a whole

No Comments

No Known Activations