INDEX

Explanations

questions or statements ending in a question mark

oai_token-act-pair · gpt-3.5-turbo

conversational phrases and rhetorical questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

places

-0.74

chairs

-0.69

gra

-0.68

cedes

-0.65

forts

-0.65

lly

-0.61

chat

-0.61

 stag

-0.60

ties

-0.59

inside

-0.59

POSITIVE LOGITS

 Thou

0.76

 thou

0.70

 anybody

0.68

ya

0.67

 ILCS

0.66

 there

0.66

YOU

0.63

Ya

0.62

 THEY

0.62

 guiActiveUnfocused

0.62

Activations Density 0.112%

questions or statements ending in a question mark

conversational phrases and rhetorical questions

No Comments

No Known Activations