INDEX

Explanations

terms related to health risks and medical conditions

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to health risks and diseases

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

minus

-0.88

 largeDownload

-0.79

cles

-0.79

istas

-0.75

ulously

-0.72

REAM

-0.72

iband

-0.72

ele

-0.70

ial

-0.68

ãĤ¢ãĥ«

-0.68

POSITIVE LOGITS

 occurrence

1.02

 miscarriage

0.98

 disease

0.93

 diseases

0.91

 adverse

0.90

 infection

0.89

 harm

0.88

 cardiovascular

0.88

 relapse

0.85

 chromos

0.83

Activations Density 0.126%

terms related to health risks and medical conditions

phrases and terms related to health risks and diseases

No Comments

No Known Activations