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

inational

-0.79

empl

-0.74

eared

-0.69

odied

-0.69

unic

-0.68

monds

-0.68

successfully

-0.67

 exting

-0.67

ognitive

-0.67

insula

-0.65

POSITIVE LOGITS

ttes

0.72

 Rasm

0.70

 Scorp

0.69

Nau

0.69

Vir

0.68

 Launch

0.68

Wat

0.67

 Workshop

0.66

 Preston

0.66

Haz

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.