INDEX

Explanations

phrases related to transitions or changes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "from" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

QUI

-0.95

iosyn

-0.76

jong

-0.76

blance

-0.76

packed

-0.73

vic

-0.72

Enlarge

-0.72

ancial

-0.69

few

-0.69

iest

-0.68

POSITIVE LOGITS

 afar

0.97

 whence

0.92

 thence

0.77

 obscurity

0.73

 indoors

0.68

 baseline

0.66

 conception

0.63

 Ashes

0.63

 scratch

0.61

 hating

0.60

Activations Density 0.084%

phrases related to transitions or changes

instances of the word "from" in various contexts

No Comments

No Known Activations