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

 spatial

-0.68

unal

-0.65

 procedural

-0.65

interstitial

-0.64

inence

-0.64

 isolate

-0.60

 isolation

-0.59

 theorist

-0.59

 nominal

-0.58

 gram

-0.58

POSITIVE LOGITS

ĨĴ

0.88

é¾įåĸļå£«

0.83

 CrossRef

0.82

RAFT

0.79

CLASSIFIED

0.78

\\\\\\\\\\\\\\\\

0.73

é¾

0.72

INESS

0.72

EStream

0.68

ogy

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.