INDEX

Explanations

mentions of the FDA in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to the FDA (Food and Drug Administration)

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

 Australians

-0.81

atre

-0.76

acters

-0.74

itars

-0.73

 Laur

-0.73

 istg

-0.71

isations

-0.69

 Ender

-0.69

ths

-0.68

 Eminem

-0.67

POSITIVE LOGITS

ILY

1.00

PA

1.00

REC

0.98

RC

0.95

HS

0.95

IL

0.93

HA

0.92

RA

0.90

CC

0.89

OC

0.89

Activations Density 0.056%

mentions of the FDA in different contexts

references to the FDA (Food and Drug Administration)

No Comments

No Known Activations