INDEX

Explanations

terms related to purity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "pure" and its associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

apter

-0.88

 closest

-0.72

pta

-0.70

 prominently

-0.68

 challeng

-0.67

 Peninsula

-0.66

ieri

-0.65

agements

-0.64

azel

-0.64

otos

-0.63

POSITIVE LOGITS

bred

1.17

waters

0.95

blood

0.93

blooded

0.87

st

0.86

0.81

 vanilla

0.76

hide

0.75

ances

0.75

 evil

0.74

Activations Density 0.020%

terms related to purity

occurrences of the word "pure" and its associations

No Comments

No Known Activations