INDEX

Explanations

mentions of sports teams, specifically the Kansas City Chiefs

oai_token-act-pair · gpt-3.5-turbo

references to "Chiefs" in the context of sports or organizational titles

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

mble

-0.98

nces

-0.88

enza

-0.88

ently

-0.87

tem

-0.82

ting

-0.81

pmwiki

-0.80

encers

-0.78

furt

-0.73

ted

-0.72

POSITIVE LOGITS

 Chiefs

0.98

doms

0.73

 Lumpur

0.67

quad

0.65

 Commissioners

0.64

 Cycle

0.61

MET

0.61

mail

0.61

 Council

0.59

Activations Density 0.025%

mentions of sports teams, specifically the Kansas City Chiefs

references to "Chiefs" in the context of sports or organizational titles

No Comments

No Known Activations