INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 Daesh

-2.94

 Syrian

-2.90

 Cousins

-2.85

 Cambodia

-2.81

 Scion

-2.72

Song

-2.71

 Cambod

-2.70

 Libyan

-2.67

 Mourinho

-2.65

Naj

-2.65

POSITIVE LOGITS

GBT

2.98

ted

2.95

 clerks

2.84

 scrut

2.84

 electr

2.79

 volts

2.78

 volt

2.78

vt

2.74

 ELECT

2.71

elect

2.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.