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

 catapult

-0.70

ordinate

-0.62

Beck

-0.61

 Desmond

-0.60

ATES

-0.60

CHAR

-0.58

ochet

-0.57

%:

-0.57

CTV

-0.57

 Chiefs

-0.55

POSITIVE LOGITS

soever

0.82

Downloadha

0.77

umbn

0.67

farm

0.66

 Gutenberg

0.66

0.65

ql

0.63

 Mongo

0.62

ugg

0.62

icas

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.