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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ellar

-0.74

ciating

-0.74

itating

-0.69

addon

-0.69

enza

-0.69

hetti

-0.68

iere

-0.67

olesc

-0.67

Queue

-0.67

itated

-0.66

POSITIVE LOGITS

vind

0.68

ership

0.67

CAP

0.64

Wo

0.62

 Voice

0.60

 POWER

0.60

 presidency

0.60

WC

0.59

 AMERICA

0.58

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.