INDEX

Explanations

mentions of interactions with or attributes related to colleagues

oai_token-act-pair · gpt-3.5-turbo

references to colleagues and collaborative relationships

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

sole

-0.76

 Ukrain

-0.75

amac

-0.73

aval

-0.70

apor

-0.66

skinned

-0.66

si

-0.65

finger

-0.64

 Tycoon

-0.59

icted

-0.58

POSITIVE LOGITS

 colleagues

1.06

 colleague

0.93

ries

0.81

é¾įå¥ĳå£«

0.80

 coworkers

0.80

ority

0.78

 classmates

0.75

heses

0.69

rious

0.67

 members

0.66

Activations Density 0.033%

mentions of interactions with or attributes related to colleagues

references to colleagues and collaborative relationships

No Comments

No Known Activations