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

deals

-0.84

yu

-0.72

deck

-0.71

 Winners

-0.70

î

-0.69

orah

-0.69

uses

-0.68

utics

-0.66

deal

-0.65

Øª

-0.65

POSITIVE LOGITS

 coerc

0.81

ortunately

0.73

 Argon

0.71

 nodd

0.70

 atmosp

0.69

 suscept

0.69

 conflicting

0.65

 Crawford

0.64

isphere

0.64

born

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.