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

osi

-0.74

psey

-0.70

zzle

-0.69

ript

-0.68

erest

-0.68

 liner

-0.68

 abundantly

-0.68

hetti

-0.67

 Mandatory

-0.67

oresc

-0.66

POSITIVE LOGITS

ãĥī

0.73

Materials

0.72

lees

0.71

dust

0.70

rising

0.69

quest

0.69

=-=-

0.67

Child

0.65

Join

0.65

Chair

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.