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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.05

2:0.09

3:0.09

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.10

11:0.09

Negative Logits

 TAMADRA

-1.87

 Surviv

-1.81

 curfew

-1.79

 Nightmares

-1.64

��

-1.63

 outing

-1.63

 Pione

-1.62

 Occupations

-1.52

 initiation

-1.52

 Encounter

-1.51

POSITIVE LOGITS

iliate

1.88

ogyn

1.82

Font

1.80

hematically

1.70

ract

1.70

SY

1.68

uly

1.68

inately

1.67

ailable

1.67

ocate

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.