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

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.06

2:0.08

3:0.08

4:0.07

5:0.06

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

hang

-1.91

pard

-1.84

 Released

-1.77

Released

-1.76

seq

-1.75

itled

-1.72

 hatched

-1.67

release

-1.66

ause

-1.63

omsday

-1.62

POSITIVE LOGITS

 Eucl

1.82

�

1.66

 Mason

1.59

 Alto

1.58

�

1.57

�

1.51

�

1.50

 Fraz

1.47

 inclination

1.47

 Colo

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.