INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 Watts

-1.82

 Irwin

-1.81

urally

-1.61

 outp

-1.58

 Sund

-1.56

 Samuel

-1.55

 Newport

-1.54

JR

-1.54

 Anderson

-1.53

 Midwest

-1.53

POSITIVE LOGITS

 ensl

1.76

cake

1.74

slaught

1.71

heid

1.71

hran

1.66

sle

1.65

モ

1.65

EVA

1.59

odka

1.57

<?

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.