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

 Pound

-0.79

 Webb

-0.69

 Sight

-0.68

 Shed

-0.68

 Nest

-0.68

 Zion

-0.68

Pug

-0.67

Rus

-0.65

 Lodge

-0.64

 Galile

-0.64

POSITIVE LOGITS

api

0.78

mentation

0.76

ano

0.71

verage

0.71

milo

0.70

ressive

0.70

igen

0.69

aic

0.69

enhagen

0.69

apy

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.