INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

soever

-0.72

ienced

-0.69

neath

-0.67

leground

-0.66

INGS

-0.64

plings

-0.63

okia

-0.63

ftime

-0.61

escription

-0.60

issy

-0.60

POSITIVE LOGITS

ropolis

0.68

xy

0.67

ca

0.65

 Radiation

0.65

rag

0.62

uria

0.62

icide

0.62

nuclear

0.60

umps

0.59

but

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.