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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

rawdownloadcloneembedreportprint

-2.94

Fam

-2.80

ici

-2.62

pmwiki

-2.56

 plur

-2.56

Creat

-2.53

 Forth

-2.53

encia

-2.49

 Corpus

-2.48

ENC

-2.43

POSITIVE LOGITS

 POLITICO

2.77

 VIDEOS

2.67

onite

2.60

 hammered

2.54

HRC

2.52

inois

2.51

�

2.48

cks

2.48

HUD

2.47

—-

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.