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

enegger

-0.84

 Antar

-0.72

 ende

-0.71

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.71

endez

-0.69

ailability

-0.68

aukee

-0.68

ktop

-0.67

 Instr

-0.66

clerosis

-0.66

POSITIVE LOGITS

ts

0.70

 cleaner

0.68

tru

0.67

 squash

0.67

 lord

0.67

 clean

0.66

 squat

0.66

pod

0.65

 oppress

0.64

liness

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.