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

onew

-0.72

locked

-0.68

 honour

-0.65

ocracy

-0.62

rimination

-0.62

Naz

-0.62

 neutrality

-0.60

uga

-0.59

freedom

-0.58

icides

-0.58

POSITIVE LOGITS

AMI

0.77

engers

0.62

RTX

0.62

 Carlson

0.62

AS

0.61

larg

0.61

~~~~~~~~~~~~~~~~

0.60

 resemb

0.59

 Dimensions

0.59

 Adult

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.