INDEX

Explanations

mentions of being or actions related to being drunk

oai_token-act-pair · gpt-3.5-turbo

references to alcohol consumption and its consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Downloadha

-0.79

akeru

-0.78

pha

-0.71

DonaldTrump

-0.70

JPM

-0.69

":["

-0.68

 Flavoring

-0.67

ILA

-0.64

 fasc

-0.64

CVE

-0.64

POSITIVE LOGITS

 drunk

1.10

bott

0.93

ards

0.91

 underage

0.88

 binge

0.87

 drinking

0.86

 drinkers

0.84

cohol

0.82

 alcohol

0.82

 drunken

0.80

Activations Density 0.019%

mentions of being or actions related to being drunk

references to alcohol consumption and its consequences

No Comments

No Known Activations