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

ko

-0.74

âĶģ

-0.69

UGC

-0.65

abella

-0.64

boro

-0.63

hou

-0.63

 Grimes

-0.63

theless

-0.63

inally

-0.63

cloth

-0.63

POSITIVE LOGITS

Words

0.65

¥ŀ

0.64

Zed

0.63

 slur

0.63

 vaccines

0.59

 forks

0.59

 ancestor

0.59

 refuge

0.58

 workspace

0.57

 Bulls

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.