INDEX

Explanations

terms related to success or victory

oai_token-act-pair · gpt-3.5-turbo

references to "winning" 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 @ 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

heter

-0.75

ensor

-0.72

opian

-0.71

anium

-0.71

ugu

-0.70

trak

-0.69

Downloadha

-0.69

del

-0.68

rouch

-0.68

thening

-0.68

POSITIVE LOGITS

 bidder

0.96

 streak

0.93

 streaks

0.81

 Eleven

0.72

 coach

0.70

MVP

0.64

 Rookie

0.63

athan

0.63

 Coach

0.63

STON

0.62

Activations Density 0.014%

terms related to success or victory

references to "winning" in various contexts

No Comments

No Known Activations