INDEX

Explanations

direct speech actions

oai_token-act-pair · gpt-3.5-turbo

statements or claims related to admissions or confessions

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

patch

-0.75

paralle

-0.69

eland

-0.68

intendent

-0.67

osi

-0.66

tail

-0.65

omorphic

-0.64

population

-0.64

lite

-0.64

cham

-0.64

POSITIVE LOGITS

 remorse

0.96

 confessed

0.91

 confess

0.91

 regrets

0.76

 calmly

0.75

 confession

0.74

 vehemently

0.71

 repeatedly

0.70

 apologized

0.70

 innocence

0.70

Activations Density 0.411%

direct speech actions

statements or claims related to admissions or confessions

No Comments

No Known Activations