INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

HOU

-0.67

Ü

-0.65

OVA

-0.65

GGGGGGGG

-0.65

BRE

-0.63

BUS

-0.61

encer

-0.61

Nation

-0.60

VILLE

-0.60

ODY

-0.59

POSITIVE LOGITS

igree

0.87

ses

0.66

lasses

0.65

 Kath

0.64

accompanied

0.64

abled

0.64

anguages

0.63

pse

0.63

esthetic

0.63

Ì¶

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.