INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

psey

-0.82

vertisement

-0.77

apore

-0.76

 tiss

-0.75

 sacrific

-0.72

onut

-0.67

 coerc

-0.67

ividual

-0.67

ilater

-0.65

oun

-0.64

POSITIVE LOGITS

soType

0.76

Introduced

0.75

wcsstore

0.71

aper

0.70

WithNo

0.69

LIN

0.69

DR

0.66

Street

0.66

 Drivers

0.66

Returns

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.