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

 sexes

-0.84

 beginnings

-0.76

 UNHCR

-0.74

 Nebula

-0.74

ãĤ«

-0.73

ãĤ¬

-0.69

ãĥ¼ãĤ¯

-0.66

 Paran

-0.65

 Elven

-0.65

ois

-0.65

POSITIVE LOGITS

terday

0.98

uma

0.69

hattan

0.67

izza

0.65

 Staten

0.65

borough

0.65

okemon

0.65

paio

0.62

 briefed

0.62

efer

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.