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

0:0.07

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.09

10:0.07

11:0.09

Negative Logits

 Spotlight

-1.72

arthy

-1.69

itely

-1.63

Untitled

-1.62

aundering

-1.59

posing

-1.55

gement

-1.55

 Vanity

-1.54

 Interior

-1.53

ilk

-1.51

POSITIVE LOGITS

ostics

2.05

 batteries

1.83

 weights

1.80

seless

1.77

 streetcar

1.74

ament

1.68

BILITY

1.68

ρ

1.64

IVES

1.64

 readers

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.