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

something

-0.67

 Traffic

-0.66

enough

-0.66

 sufficient

-0.63

training

-0.62

 SIGN

-0.61

necess

-0.61

OPLE

-0.60

THING

-0.59

 sufficiently

-0.59

POSITIVE LOGITS

 Cosponsors

0.91

assetsadobe

0.82

ahoo

0.74

fter

0.72

arnaev

0.69

ay

0.69

nell

0.69

Oracle

0.67

renches

0.67

anned

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.