INDEX

Explanations

instances where something is clearly apparent or obvious

oai_token-act-pair · gpt-3.5-turbo

instances of the word "evident" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

axter

-0.70

zanne

-0.69

berman

-0.66

wake

-0.66

EStreamFrame

-0.65

uden

-0.65

 sacked

-0.65

pered

-0.64

aird

-0.63

atern

-0.63

POSITIVE LOGITS

iary

1.42

ial

0.85

 evident

0.81

 Signs

0.80

icity

0.79

ively

0.76

ially

0.76

aneously

0.75

icative

0.75

iation

0.74

Activations Density 0.009%

instances where something is clearly apparent or obvious

instances of the word "evident" and its variations

No Comments

No Known Activations