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

%:

-0.74

 Corruption

-0.63

 boycott

-0.63

[+

-0.60

 Skydragon

-0.60

 Cruel

-0.60

rait

-0.59

MpServer

-0.58

 Span

-0.57

 ãĤµ

-0.56

POSITIVE LOGITS

iences

0.79

iment

0.71

ufact

0.65

apon

0.65

itia

0.65

 adjusts

0.64

inventoryQuantity

0.60

leground

0.59

ndra

0.59

 unlocks

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.