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

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

achine

-2.80

grim

-2.69

agh

-2.65

 horns

-2.62

secret

-2.58

SPONSORED

-2.55

esta

-2.51

lash

-2.50

amaru

-2.45

 Rath

-2.42

POSITIVE LOGITS

ibling

2.90

 comparative

2.77

Individual

2.76

 biome

2.69

 individually

2.69

ividual

2.56

�

2.52

 eclipse

2.48

 Simulation

2.44

 experien

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.