INDEX

Explanations

questions and expressions related to confusion or seeking understanding

oai_token-act-pair · gpt-3.5-turbo

expressions of confusion or questioning related to reasons

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

lator

-0.71

 Noir

-0.65

catentry

-0.65

 FINAL

-0.64

hazard

-0.64

kefeller

-0.64

odder

-0.63

aughed

-0.62

iHUD

-0.62

agonist

-0.62

POSITIVE LOGITS

 bother

0.88

why

0.75

 anybody

0.65

 anyone

0.65

 coincidence

0.65

why

0.64

 drawn

0.64

WHY

0.63

 repetition

0.62

 somebody

0.62

Activations Density 0.082%

questions and expressions related to confusion or seeking understanding

expressions of confusion or questioning related to reasons

No Comments

No Known Activations