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

vernment

-0.82

ertodd

-0.81

terson

-0.76

ournal

-0.74

azard

-0.73

encies

-0.73

Continue

-0.72

apple

-0.72

gemony

-0.72

igham

-0.71

POSITIVE LOGITS

ch

0.64

 neut

0.63

pin

0.62

def

0.61

flo

0.61

qv

0.60

ASA

0.60

 thrust

0.59

elf

0.59

sie

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.