INDEX

Explanations

phrases indicating inclusion or participation in a group or project

oai_token-act-pair · gpt-3.5-turbo

references to participation or being involved in activities or groups

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

ptive

-0.71

 ceilings

-0.70

acs

-0.68

encies

-0.68

iasis

-0.66

 assumes

-0.63

tesque

-0.62

ency

-0.62

hurst

-0.61

 incurred

-0.59

POSITIVE LOGITS

ADRA

0.78

 society

0.77

 Team

0.75

Team

0.73

team

0.71

edIn

0.70

ĪĴ

0.68

-+-+

0.68

 civilization

0.65

¬¼

0.64

Activations Density 0.111%

phrases indicating inclusion or participation in a group or project

references to participation or being involved in activities or groups

No Comments

No Known Activations