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

Quantity

-0.82

PDATE

-0.72

APTER

-0.72

XT

-0.64

Reloaded

-0.62

Clo

-0.60

 intoler

-0.59

Prem

-0.56

éļ

-0.56

 pumps

-0.56

POSITIVE LOGITS

emouth

0.77

ero

0.72

ukong

0.70

egal

0.69

icago

0.64

enture

0.64

nesota

0.64

escal

0.64

bang

0.64

imore

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.