INDEX

Explanations

sports and leisure activities

oai_token-act-pair · gpt-3.5-turbo

activities and social interactions involving games and sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 ACTIONS

-0.64

ENTION

-0.63

foreseen

-0.59

ottesville

-0.59

icularly

-0.58

cipled

-0.58

uilding

-0.58

ividually

-0.58

inarily

-0.57

ciplinary

-0.55

POSITIVE LOGITS

Jr

0.61

Magikarp

0.61

zai

0.60

Shell

0.60

Legend

0.56

 cowboy

0.55

amins

0.55

mac

0.53

 Chrom

0.52

AAA

0.52

Activations Density 1.241%

sports and leisure activities

activities and social interactions involving games and sports

No Comments

No Known Activations