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

cription

-0.80

cius

-0.77

anders

-0.76

eeds

-0.73

istries

-0.72

liness

-0.70

intend

-0.70

eton

-0.69

 GOODMAN

-0.69

agents

-0.66

POSITIVE LOGITS

uzz

0.72

Ð´

0.68

DEV

0.66

BRE

0.66

FORE

0.65

OAD

0.63

UST

0.62

FFFF

0.61

HH

0.61

Ð¼

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.