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

obal

-0.66

FN

-0.64

 outsider

-0.62

NF

-0.60

amines

-0.59

nered

-0.59

nikov

-0.58

head

-0.58

awatts

-0.58

ERG

-0.58

POSITIVE LOGITS

ESA

0.75

 Exper

0.68

 Discord

0.67

 Scand

0.67

 Leeds

0.66

Tos

0.65

 Yorkshire

0.64

tis

0.63

 Argon

0.63

 Auth

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.