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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.09

6:0.09

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

pas

-1.73

セ

-1.57

apon

-1.56

Lear

-1.50

 Span

-1.50

eas

-1.50

Reviewer

-1.44

tim

-1.43

von

-1.43

ircraft

-1.41

POSITIVE LOGITS

 competing

1.61

 undecided

1.60

 defect

1.47

 moot

1.41

icts

1.40

 Saud

1.39

elsius

1.34

 automakers

1.34

 testosterone

1.33

 merits

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.