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

ngth

-1.00

mares

-0.93

interstitial

-0.82

utterstock

-0.80

 Nguyen

-0.77

nels

-0.76

allery

-0.75

vier

-0.74

ivism

-0.74

ËĪ

-0.74

POSITIVE LOGITS

bon

0.80

riger

0.62

âĹ¼

0.61

bon

0.61

Syn

0.59

 comfort

0.58

comed

0.57

cart

0.57

Typ

0.57

 Consumption

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.