INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

Vaj

-3.38

 Radical

-2.94

anyahu

-2.78

owship

-2.71

 disliked

-2.60

 welf

-2.59

JB

-2.56

WP

-2.55

 oppressed

-2.55

LT

-2.53

POSITIVE LOGITS

 Columb

3.14

Columb

2.89

 Daytona

2.83

 Rodrig

2.61

 Pens

2.57

 Columbia

2.52

Atl

2.41

 Mississ

2.38

=#

2.36

 Charleston

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.