INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ETF

-0.73

 Seventh

-0.72

higher

-0.72

roth

-0.71

racuse

-0.71

ruary

-0.70

mpeg

-0.66

çĶ°

-0.65

ãĥģ

-0.64

ãĤĵ

-0.63

POSITIVE LOGITS

ooks

0.73

ables

0.66

advertisement

0.64

ivo

0.62

ushes

0.61

ivers

0.60

itage

0.59

 controls

0.58

angelo

0.57

balls

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.