INDEX

Explanations

technical terms related to computing or electronics, likely related to WM (working memory)

oai_token-act-pair · gpt-3.5-turbo

terms related to working memory (WM) and attention measures (WT)

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

apore

-0.67

resso

-0.65

mort

-0.65

 counselors

-0.64

otle

-0.63

 afore

-0.63

abad

-0.63

 Rica

-0.62

clinton

-0.61

anthrop

-0.61

POSITIVE LOGITS

WM

1.10

wm

0.92

WM

0.86

IPM

0.86

idth

0.79

è¦ļéĨĴ

0.78

FU

0.77

ICH

0.76

restling

0.76

Fs

0.75

Activations Density 0.019%

technical terms related to computing or electronics, likely related to WM (working memory)

terms related to working memory (WM) and attention measures (WT)

No Comments

No Known Activations