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

»

-0.65

¥ŀ

-0.65

perial

-0.64

liga

-0.64

 exha

-0.64

bell

-0.64

 Pigs

-0.63

½

-0.61

Hua

-0.61

icho

-0.60

POSITIVE LOGITS

 +---

0.72

ativity

0.70

\":

0.66

hips

0.66

AME

0.61

inations

0.60

ations

0.59

yon

0.59

 Puzzles

0.59

ative

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.