INDEX

Explanations

mentions of the word "Swift" with varying activation values indicating different strengths of association

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Swift."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ulhu

-0.70

irin

-0.69

Downloadha

-0.69

chell

-0.69

terior

-0.68

egal

-0.67

berra

-0.66

abases

-0.66

Ars

-0.65

orate

-0.65

POSITIVE LOGITS

 Swift

0.84

heart

0.81

ipeg

0.80

 Swim

0.77

lings

0.76

song

0.75

omatic

0.75

ies

0.73

blade

0.72

ness

0.72

Activations Density 0.017%

mentions of the word "Swift" with varying activation values indicating different strengths of association

mentions of the name "Swift."

No Comments

No Known Activations