INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

uador

-0.75

culosis

-0.68

 wiser

-0.63

atha

-0.61

 sleeper

-0.59

edded

-0.59

agi

-0.58

agus

-0.58

 Emperor

-0.57

hid

-0.57

POSITIVE LOGITS

 ingred

0.89

 Votes

0.80

externalActionCode

0.77

said

0.72

Demand

0.71

 Berks

0.70

+++

0.68

 ensu

0.67

mber

0.66

 Done

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.