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

IFrame

Link

Negative Logits

Mot

-0.74

prints

-0.73

ework

-0.71

Focus

-0.71

cial

-0.70

thus

-0.70

flex

-0.69

hei

-0.67

stead

-0.67

onday

-0.66

POSITIVE LOGITS

ĨĴ

0.74

 prejudice

0.72

 derog

0.69

 cringe

0.69

 genocide

0.64

GGGGGGGG

0.64

 miscarriage

0.63

 condem

0.63

 guiActiveUn

0.62

 scathing

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.