INDEX

Explanations

words related to pharmaceuticals or chemical compounds

oai_token-act-pair · gpt-3.5-turbo

mentions of scientific or medical terms and concepts

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

gerald

-0.68

inki

-0.67

EEK

-0.65

 glim

-0.64

hetically

-0.64

leness

-0.63

STEM

-0.60

bodied

-0.60

Spot

-0.60

enhagen

-0.59

POSITIVE LOGITS

atari

0.79

aic

0.77

cz

0.74

otide

0.72

ciation

0.69

©¶æ

0.69

atis

0.65

jac

0.65

 Radiation

0.64

kov

0.63

Activations Density 0.472%

words related to pharmaceuticals or chemical compounds

mentions of scientific or medical terms and concepts

No Comments

No Known Activations