INDEX

Explanations

values or quantities described within a range

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a range or variability

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

iquette

-0.76

ourage

-0.72

irlf

-0.64

ITED

-0.63

itialized

-0.61

ĺ

-0.60

ciation

-0.59

condition

-0.59

tank

-0.59

ipeg

-0.57

POSITIVE LOGITS

 afar

1.06

esides

0.64

oller

0.63

 bench

0.61

uton

0.60

 disparate

0.59

ibrary

0.59

quart

0.58

 dexter

0.58

 sideline

0.57

Activations Density 0.046%

values or quantities described within a range

phrases indicating a range or variability

No Comments

No Known Activations