INDEX

Explanations

No Explanations Found

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

sburg

-0.71

cock

-0.66

bilt

-0.65

 Nichols

-0.62

 Journals

-0.61

 Parish

-0.61

PAX

-0.61

 Winchester

-0.60

])

-0.60

 quarantine

-0.60

POSITIVE LOGITS

uner

0.71

akin

0.69

SPONSORED

0.66

isk

0.66

DIV

0.65

verage

0.62

iri

0.62

inda

0.61

ffic

0.61

Aren

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.