INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pell

-0.75

wered

-0.73

pu

-0.71

tten

-0.70

plet

-0.70

Reply

-0.68

 visits

-0.67

vg

-0.66

tle

-0.66

 reconc

-0.66

POSITIVE LOGITS

 Cortex

0.72

ulia

0.65

Ops

0.64

 Dynam

0.61

conom

0.60

 Arms

0.60

 Franch

0.60

DDR

0.60

issance

0.60

oreal

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.