INDEX

Explanations

comparisons between different concepts or entities

oai_token-act-pair · gpt-3.5-turbo

comparative phrases or constructions that evaluate differences between entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

etsk

-0.69

ista

-0.69

iken

-0.66

assadors

-0.66

istar

-0.65

encers

-0.65

eni

-0.64

 Instructor

-0.63

rica

-0.62

rend

-0.61

POSITIVE LOGITS

 fingerprints

0.89

 homosexuality

0.81

 murder

0.77

 wildfire

0.76

lihood

0.76

 incest

0.76

 circumcision

0.75

 ours

0.74

any

0.73

 alcoholism

0.72

Activations Density 0.258%

comparisons between different concepts or entities

comparative phrases or constructions that evaluate differences between entities or concepts

No Comments

No Known Activations