INDEX

Explanations

medical and scientific terms related to diseases, disorders, and substances

oai_token-act-pair · gpt-3.5-turbo

terms related to health, diseases, and related scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

herty

-0.72

ãĥĥ

-0.70

 Dull

-0.69

hiro

-0.69

 haunt

-0.69

æ©

-0.68

staking

-0.67

²¾

-0.65

 Warn

-0.65

Sne

-0.64

POSITIVE LOGITS

 syndrome

0.82

âĢ¢âĢ¢

0.79

Â®,

0.73

eers

0.73

(<

0.71

(>

0.69

;;;;;;;;;;;;

0.69

Â®

0.68

ploma

0.65

 equivalents

0.65

Activations Density 0.264%

medical and scientific terms related to diseases, disorders, and substances

terms related to health, diseases, and related scientific concepts

No Comments

No Known Activations