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

thood

-0.79

 Puzz

-0.69

 Neon

-0.65

 Tradable

-0.62

 habit

-0.62

FACE

-0.62

PDATE

-0.62

icol

-0.61

 Employ

-0.61

 Inst

-0.60

POSITIVE LOGITS

plet

0.69

atta

0.66

rists

0.64

fficiency

0.61

antics

0.61

 resultant

0.61

oning

0.60

onement

0.60

retch

0.60

metry

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.