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

Bey

-0.77

 predec

-0.72

merce

-0.71

 comr

-0.69

 bombard

-0.62

 testim

-0.61

Interested

-0.61

 accomp

-0.61

amples

-0.60

oÄŁ

-0.60

POSITIVE LOGITS

walker

0.66

çĶŁ

0.64

 Swanson

0.63

 Robotics

0.62

 tree

0.62

ursor

0.62

 Hawkins

0.60

 hots

0.59

asket

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.