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

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.10

11:0.07

Negative Logits

 Citation

-3.70

Â

-3.06

 Spoiler

-2.93

 Pole

-2.92

 Judicial

-2.88

 Owners

-2.87

 Citiz

-2.86

 Tire

-2.85

 Prism

-2.85

 Theft

-2.83

POSITIVE LOGITS

anwhile

3.17

 hurd

2.96

ctrl

2.86

eport

2.75

eon

2.74

 carbohyd

2.62

minus

2.57

 submar

2.54

ERG

2.50

 halt

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.