INDEX

Explanations

phrases related to guiding or leading someone to a destination or experience

oai_token-act-pair · gpt-3.5-turbo

references to directions or pathways leading to specific destinations or experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vine

-0.69

icipated

-0.65

stock

-0.61

cised

-0.58

creen

-0.57

ored

-0.55

 slips

-0.54

 ende

-0.54

uracy

-0.53

 extent

-0.53

POSITIVE LOGITS

 nowhere

0.92

 onwards

0.91

 aback

0.86

 onward

0.86

 toward

0.83

 closer

0.80

 towards

0.80

 into

0.80

Ô

0.77

into

0.76

Activations Density 0.133%

phrases related to guiding or leading someone to a destination or experience

references to directions or pathways leading to specific destinations or experiences

No Comments

No Known Activations