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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iro

-0.65

jar

-0.65

 biod

-0.64

 Leap

-0.62

vernment

-0.61

ophers

-0.61

irlf

-0.61

 bark

-0.61

aucuses

-0.61

indal

-0.61

POSITIVE LOGITS

tch

0.77

 bluff

0.70

Ĥª

0.67

nan

0.66

Http

0.66

 leve

0.65

dden

0.65

 guiActiveUn

0.64

pole

0.62

 Vert

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.