INDEX

Explanations

words related to scoring in sports

oai_token-act-pair · gpt-3.5-turbo

references to scoring or goals in sports 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

 Breed

-0.67

é¾įå¥ĳå£«

-0.66

tan

-0.65

 vacc

-0.62

fell

-0.62

 suit

-0.61

 pedd

-0.59

 plur

-0.59

 gent

-0.59

agan

-0.58

POSITIVE LOGITS

card

0.89

ific

0.87

emi

0.86

keeper

0.86

rs

0.85

ificial

0.84

 scored

0.83

cards

0.83

ificant

0.82

 scoring

0.82

Activations Density 0.021%

words related to scoring in sports

references to scoring or goals in sports contexts

No Comments

No Known Activations