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

nel

-0.76

unal

-0.70

idon

-0.67

cul

-0.65

nell

-0.64

onet

-0.61

sed

-0.61

illac

-0.59

annis

-0.58

 Commodore

-0.57

POSITIVE LOGITS

omen

0.70

ibaba

0.67

 Takeru

0.64

raq

0.64

osponsors

0.64

LAN

0.64

anwhile

0.64

uyomi

0.64

hetti

0.62

rity

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.