INDEX

Explanations

words related to teamwork and collaboration

oai_token-act-pair · gpt-3.5-turbo

mentions of "team" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

fect

-0.79

pire

-0.75

thy

-0.70

va

-0.70

nces

-0.69

Accessory

-0.69

Maw

-0.68

ocene

-0.68

tml

-0.68

judicial

-0.66

POSITIVE LOGITS

 mates

1.10

 team

0.92

 mate

0.91

 teams

0.85

mates

0.81

team

0.80

liquid

0.79

 colleagues

0.78

 manager

0.77

alion

0.75

Activations Density 0.056%

words related to teamwork and collaboration

mentions of "team" in various contexts

No Comments

No Known Activations