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

ãĥ¼ãĥĨ

-0.69

furt

-0.68

 Celest

-0.67

 Kinnikuman

-0.65

emen

-0.65

GE

-0.65

ãĥĥãĥī

-0.64

 override

-0.64

src

-0.61

 Demons

-0.61

POSITIVE LOGITS

eree

0.83

 Chaser

0.67

dyl

0.67

poon

0.66

issors

0.63

reci

0.63

letters

0.62

 Quote

0.61

igator

0.60

doors

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.