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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isol

-0.73

atform

-0.71

Interstitial

-0.69

 misunder

-0.69

thora

-0.68

icter

-0.68

External

-0.64

 Boll

-0.64

Asia

-0.63

 unbeliev

-0.62

POSITIVE LOGITS

qv

0.72

uers

0.70

ynt

0.69

gren

0.68

iferation

0.67

tracking

0.67

 Janeiro

0.66

laughs

0.63

pun

0.63

ner

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.