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

luck

-0.87

Examples

-0.78

NESS

-0.76

Dutch

-0.73

Did

-0.71

CW

-0.70

NB

-0.70

oons

-0.69

duc

-0.69

Discover

-0.69

POSITIVE LOGITS

 raft

0.86

 whopping

0.83

 mammoth

0.75

lot

0.73

 growing

0.73

 disparate

0.72

 handful

0.71

orah

0.69

 bunch

0.69

rouse

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.