INDEX

Explanations

keywords related to medical conditions, stimulants, and specific medications like ADHD, caffeine, and amphetamines

oai_token-act-pair · gpt-3.5-turbo

references to ADHD and related stimulants or medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ĪĴ

-0.84

din

-0.75

 Rouge

-0.73

bis

-0.71

bian

-0.71

erial

-0.69

esome

-0.69

 Aires

-0.68

cies

-0.68

Bone

-0.68

POSITIVE LOGITS

 stimul

1.20

hetamine

0.91

 caffeine

0.82

committee

0.79

 relapse

0.78

 ADHD

0.75

 medication

0.75

inson

0.75

 impuls

0.73

 neurot

0.70

Activations Density 0.019%

keywords related to medical conditions, stimulants, and specific medications like ADHD, caffeine, and amphetamines

references to ADHD and related stimulants or medications

No Comments

No Known Activations