INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Syn

-0.75

oys

-0.74

kes

-0.71

itialized

-0.69

 Axis

-0.69

 Wolves

-0.67

 Trials

-0.66

ipeg

-0.65

semb

-0.63

 Devils

-0.62

POSITIVE LOGITS

ifice

0.81

senal

0.76

 suspic

0.74

 Fernand

0.74

 Trayvon

0.74

 metic

0.71

 blat

0.71

 entreprene

0.68

ULTS

0.66

 adolesc

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.