INDEX

Explanations

acronyms or initials used in specific contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letters "EW" in various formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idy

-0.66

cephal

-0.65

cy

-0.61

thood

-0.61

tera

-0.60

cel

-0.59

ority

-0.59

 Monteneg

-0.58

usher

-0.58

mas

-0.58

POSITIVE LOGITS

ITNESS

1.16

estern

1.09

restling

0.93

nesday

0.90

een

0.89

ORD

0.87

yk

0.86

riter

0.85

Ö¼

0.85

ARDS

0.85

Activations Density 0.016%

acronyms or initials used in specific contexts

occurrences of the letters "EW" in various formats

No Comments

No Known Activations