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

0:0.08

1:0.07

2:0.08

3:0.07

4:0.09

5:0.06

6:0.07

7:0.10

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 screenings

-1.76

 misplaced

-1.64

 sneaking

-1.59

 Revelations

-1.58

lies

-1.57

 locating

-1.55

 Homeland

-1.54

 Grande

-1.52

 unfounded

-1.52

 Awakening

-1.46

POSITIVE LOGITS

mbuds

2.13

oun

1.97

�

1.88

edom

1.83

undrum

1.81

 Leilan

1.79

arbon

1.78

otom

1.68

netflix

1.66

────

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.