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

Not in Any Lists

No Comments

Negative Logits

cffff

-0.83

 Virtue

-0.76

theless

-0.73

 adolesc

-0.71

 opio

-0.70

ourse

-0.66

 commun

-0.66

 Qiao

-0.65

 Brach

-0.64

 derog

-0.63

POSITIVE LOGITS

chn

0.87

pak

0.80

TERN

0.73

RAW

0.72

tex

0.71

zman

0.70

DES

0.70

cko

0.69

ARCH

0.69

chell

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.