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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FTWARE

-0.76

ptions

-0.64

INGTON

-0.63

 Alexandria

-0.63

 Jericho

-0.62

 Valhalla

-0.62

 Scotia

-0.61

ãĥķãĤ©

-0.61

abin

-0.61

 Isles

-0.60

POSITIVE LOGITS

immune

0.75

rog

0.70

cus

0.68

ento

0.68

anim

0.66

 Probe

0.65

iris

0.64

 Grac

0.63

icter

0.63

usk

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.