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

-0.82

iors

-0.75

laus

-0.74

ickets

-0.73

culosis

-0.72

Ton

-0.65

Tan

-0.64

 Tales

-0.64

 castles

-0.63

 Cabin

-0.62

POSITIVE LOGITS

 DISTR

0.66

ihil

0.66

esp

0.64

GHz

0.64

ESV

0.63

ENN

0.62

enson

0.62

uminati

0.62

ENG

0.61

ITNESS

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.