INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 chronically

-0.80

 concurrently

-0.73

 diaper

-0.72

 contagious

-0.71

 trave

-0.70

 therape

-0.69

 unpredict

-0.68

 withd

-0.68

ĸļ

-0.67

 soap

-0.66

POSITIVE LOGITS

pn

0.84

 theirs

0.76

hak

0.75

 Ended

0.73

 hers

0.73

eous

0.70

went

0.69

 Authorization

0.69

 Preservation

0.69

phabet

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.