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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 partName

-0.71

 inhibitor

-0.65

=#

-0.62

Cooldown

-0.61

 residual

-0.61

 refere

-0.60

 Mandatory

-0.59

 VICE

-0.59

rim

-0.59

bard

-0.58

POSITIVE LOGITS

trust

0.84

iture

0.73

Trust

0.71

kr

0.69

acity

0.68

ACY

0.67

 laure

0.66

chio

0.66

amins

0.65

ĸļ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.