INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

*/(

-0.85

ilts

-0.68

Appearances

-0.68

ential

-0.67

 protector

-0.65

 interven

-0.64

atever

-0.63

 Ajax

-0.62

abeth

-0.62

ucket

-0.61

POSITIVE LOGITS

liga

0.90

perm

0.66

igrants

0.65

igrate

0.65

mand

0.64

isconsin

0.64

wik

0.62

atoon

0.61

Wiki

0.60

sbm

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.