INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

akings

-0.74

iets

-0.68

ntil

-0.68

nea

-0.67

perties

-0.65

kins

-0.65

ombs

-0.64

letal

-0.64

 pricing

-0.63

chers

-0.62

POSITIVE LOGITS

AppData

0.78

hani

0.70

æĥ

0.67

 Casino

0.66

 Masquerade

0.65

Cth

0.63

warm

0.61

isl

0.61

 Gork

0.60

 poker

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.