INDEX

Explanations

No Explanations Found

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Family

-1.86

版

-1.70

ゼウス

-1.70

-1.66

Director

-1.62

=-=-=-=-

-1.62

 Powered

-1.59

 Advertisement

-1.56

 Letters

-1.55

Voice

-1.55

POSITIVE LOGITS

 coff

1.69

 practise

1.66

 airflow

1.65

rave

1.65

tem

1.60

lier

1.57

 footing

1.56

iably

1.55

 fault

1.55

 cycling

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.