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

EA

-0.74

ESA

-0.69

EVA

-0.62

Els

-0.62

UGE

-0.61

ATHER

-0.60

LU

-0.60

egal

-0.60

esh

-0.59

 Strip

-0.59

POSITIVE LOGITS

bats

0.76

enhagen

0.72

athing

0.68

cases

0.66

otypes

0.66

itbart

0.66

ueless

0.66

spect

0.66

posium

0.66

ournal

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.