INDEX

Explanations

phrases related to animals, especially birds of prey

oai_token-act-pair · gpt-3.5-turbo

possessive forms and idiomatic expressions related to ownership or sharing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 horizont

-0.80

 fortun

-0.75

ascript

-0.70

FUL

-0.69

quickShipAvailable

-0.67

 experien

-0.65

 superiors

-0.62

unda

-0.62

tul

-0.61

 goodbye

-0.61

POSITIVE LOGITS

bane

0.91

eye

0.84

Eye

0.76

ombat

0.74

aviour

0.74

dog

0.72

otted

0.71

footed

0.71

 paws

0.69

poke

0.69

Activations Density 0.176%

phrases related to animals, especially birds of prey

possessive forms and idiomatic expressions related to ownership or sharing

No Comments

No Known Activations