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

 brist

-0.70

psc

-0.67

ãĥ¼ãĥĨ

-0.66

toggle

-0.65

swick

-0.63

 sshd

-0.62

yg

-0.62

actions

-0.62

sonian

-0.61

 Spac

-0.60

POSITIVE LOGITS

illac

0.77

osion

0.68

avis

0.66

asm

0.66

asma

0.65

odus

0.64

cellence

0.64

raved

0.64

ocese

0.64

 theology

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.