INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Federation

-0.65

 Continental

-0.63

 federation

-0.61

 Philippine

-0.61

Classic

-0.61

 Cumm

-0.60

atti

-0.59

 Spokane

-0.59

©¶æ¥µ

-0.59

 NAFTA

-0.58

POSITIVE LOGITS

orthy

0.78

gomery

0.75

bes

0.73

imens

0.73

oser

0.72

umn

0.71

ospons

0.71

inel

0.70

ocrats

0.69

 priorit

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.