INDEX

Explanations

phrases related to size or magnitude

oai_token-act-pair · gpt-3.5-turbo

terms related to measurement and magnitude

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

enegger

-0.72

ocally

-0.68

inos

-0.66

Eva

-0.66

inis

-0.65

inka

-0.65

 Advertisement

-0.64

isse

-0.64

hedon

-0.61

romeda

-0.59

POSITIVE LOGITS

of

0.98

 thereof

0.91

iest

0.88

 level

0.75

 extent

0.73

liest

0.73

natureconservancy

0.72

OF

0.71

iness

0.70

 similarities

0.69

Activations Density 0.257%

phrases related to size or magnitude

terms related to measurement and magnitude

No Comments

No Known Activations