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

otle

-0.69

alog

-0.67

 Zeal

-0.65

oyd

-0.64

urban

-0.64

romeda

-0.64

atu

-0.62

************

-0.61

)</

-0.58

POSITIVE LOGITS

iculty

0.74

abilities

0.73

ptoms

0.70

 CLSID

0.67

?]

0.66

pid

0.66

 McDonnell

0.64

nyder

0.63

 glim

0.63

detail

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.