INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

abee

-0.77

ãĤ´ãĥ³

-0.73

rongh

-0.69

ãĥ³ãĤ¸

-0.68

ptin

-0.67

 developmental

-0.66

 dysfunction

-0.65

 turnover

-0.65

kefeller

-0.64

iscal

-0.63

POSITIVE LOGITS

ilk

0.76

 pencil

0.64

 Beware

0.64

 Graph

0.63

 accus

0.62

 Fold

0.62

maid

0.61

tip

0.61

Chain

0.61

Featured

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.