INDEX

Explanations

phrases related to arrays or collections

oai_token-act-pair · gpt-3.5-turbo

references to "array" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

doms

-0.69

WAR

-0.69

 Whitman

-0.66

ews

-0.65

dom

-0.64

SG

-0.64

 Gold

-0.63

SF

-0.62

Ur

-0.60

 Trade

-0.60

POSITIVE LOGITS

 array

1.05

array

0.89

mble

0.86

 subscript

0.86

 arrays

0.86

icter

0.78

moil

0.71

 orchestr

0.70

uably

0.70

 Array

0.69

Activations Density 0.009%

phrases related to arrays or collections

references to "array" in various contexts

No Comments

No Known Activations