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

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

notations

-1.82

itle

-1.79

Ing

-1.78

 trademarks

-1.74

click

-1.73

Article

-1.70

drawn

-1.69

xxxxxxxx

-1.68

starter

-1.67

please

-1.63

POSITIVE LOGITS

icans

1.84

alus

1.75

 Juliet

1.73

 Palestin

1.72

 Laurent

1.65

bda

1.64

tsky

1.60

 resil

1.59

lehem

1.57

 Desmond

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.