INDEX

Explanations

mentions of medical conditions or terms related to medications and science

oai_token-act-pair · gpt-3.5-turbo

terms related to medical conditions and their effects

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

orer

-0.74

ational

-0.74

DERR

-0.74

orers

-0.68

IBLE

-0.68

ORED

-0.66

IFIED

-0.66

arium

-0.66

ained

-0.63

RELATED

-0.61

POSITIVE LOGITS

ramid

1.02

Å«

0.98

ramids

0.88

chev

0.84

stery

0.83

lene

0.82

mbol

0.82

ptoms

0.80

ey

0.79

mit

0.79

Activations Density 0.046%

mentions of medical conditions or terms related to medications and science

terms related to medical conditions and their effects

No Comments

No Known Activations