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

eteria

-0.84

ADRA

-0.72

 Hearth

-0.72

iquette

-0.71

 Goat

-0.66

 encount

-0.65

 Clan

-0.64

anwhile

-0.64

roots

-0.64

sha

-0.64

POSITIVE LOGITS

 democrat

0.71

 robber

0.65

 visitation

0.62

olation

0.61

 dollars

0.61

 tracts

0.60

 impulse

0.60

 susp

0.60

 microsc

0.60

 privat

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.