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

0:0.08

1:0.08

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

 doct

-2.94

 scrut

-2.75

pol

-2.66

 retri

-2.59

piv

-2.57

bog

-2.51

�

-2.50

 Burr

-2.47

tro

-2.46

idav

-2.44

POSITIVE LOGITS

Glass

2.92

wine

2.86

Eat

2.62

tones

2.57

hots

2.53

Gaza

2.53

ayne

2.48

Food

2.47

Han

2.45

Hong

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.