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

1:0.08

2:0.07

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

ORED

-1.85

 arsen

-1.82

 reperto

-1.80

ABV

-1.69

ortment

-1.64

sor

-1.64

acebook

-1.63

onomy

-1.63

 sexes

-1.61

 MISS

-1.60

POSITIVE LOGITS

Hope

1.70

tsky

1.61

ermanent

1.61

ulk

1.57

cells

1.54

eland

1.49

 compensated

1.49

 negativity

1.47

idious

1.47

idy

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.