INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

arantine

-3.34

ective

-3.21

brance

-3.12

allery

-3.10

enegger

-3.06

nsics

-2.99

spection

-2.95

.;

-2.89

icter

-2.87

ciation

-2.86

POSITIVE LOGITS

Veg

2.83

Sin

2.75

 greens

2.72

 Negro

2.71

Gan

2.68

 prostitutes

2.53

apeake

2.43

Sin

2.42

 Blacks

2.42

 Chick

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.