INDEX

Explanations

terms related to gambling, specifically focusing on poker

oai_token-act-pair · gpt-3.5-turbo

mentions of poker and related gambling concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rians

-0.84

rum

-0.79

edly

-0.72

ufact

-0.70

 Matter

-0.69

mentation

-0.68

anwhile

-0.68

ean

-0.65

 diverse

-0.64

produced

-0.64

POSITIVE LOGITS

 poker

1.05

Stars

1.01

halla

0.82

 betting

0.80

 gambling

0.80

tery

0.76

 Poker

0.76

stars

0.75

bowl

0.74

kered

0.74

Activations Density 0.018%

terms related to gambling, specifically focusing on poker

mentions of poker and related gambling concepts

No Comments

No Known Activations