INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bun

-0.71

atics

-0.69

gradient

-0.67

"}

-0.66

UCT

-0.64

inator

-0.64

 Bengal

-0.62

adder

-0.61

acle

-0.60

inal

-0.60

POSITIVE LOGITS

 GOODMAN

0.67

ãĤ¨ãĥ«

0.66

ILY

0.64

 Wass

0.64

 corrid

0.63

arus

0.61

 Rossi

0.60

KNOWN

0.60

leep

0.60

wrapper

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.