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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 actionGroup

-0.81

osite

-0.79

soType

-0.74

)]

-0.71

Ô

-0.69

 rall

-0.68

ussen

-0.68

Ã¡n

-0.65

phal

-0.65

OPA

-0.65

POSITIVE LOGITS

tiny

0.76

ugar

0.71

 acre

0.67

 cubic

0.66

pox

0.66

heter

0.65

 bucks

0.64

ede

0.64

profits

0.64

ishy

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.