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

 Jobs

-0.73

 Goodell

-0.70

 Ellison

-0.65

 Canal

-0.65

 Depression

-0.64

inner

-0.64

 Dungeon

-0.62

arios

-0.61

OPLE

-0.61

Ou

-0.61

POSITIVE LOGITS

 simultane

0.71

ãħĭãħĭ

0.69

bral

0.69

pite

0.69

pson

0.67

 scient

0.67

nown

0.67

SCP

0.67

AAF

0.65

pace

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.