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

 mathemat

-0.85

yrus

-0.84

emort

-0.82

 accur

-0.81

 destro

-0.81

 therap

-0.79

 comr

-0.78

 streng

-0.75

ĳå£«

-0.75

 guiActiveUnfocused

-0.74

POSITIVE LOGITS

ets

0.74

lein

0.71

umed

0.67

 Senators

0.67

 Crisis

0.67

DD

0.66

 Ways

0.66

 Congressman

0.63

 Representatives

0.62

cuts

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.