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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

�

-3.95

Thompson

-3.10

orc

-3.01

Hig

-2.98

TB

-2.89

iuses

-2.88

 Neph

-2.87

enth

-2.77

Magikarp

-2.77

igr

-2.77

POSITIVE LOGITS

Cue

2.79

 Extend

2.59

–

2.54

 REUTERS

2.54

 Nato

2.50

 tease

2.49

 enrichment

2.48

 conting

2.41

 Coco

2.39

 Cairo

2.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.