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

Head Attr Weights

0:0.09

1:0.06

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

thood

-2.28

folios

-1.91

ageddon

-1.76

markets

-1.76

 representation

-1.73

 increments

-1.67

 portfolios

-1.67

rift

-1.64

ruary

-1.62

ighters

-1.61

POSITIVE LOGITS

Reporting

1.77

mb

1.73

NOW

1.66

 AUTHOR

1.65

Emb

1.60

*)

1.53

ns

1.53

KB

1.50

mal

1.50

Grant

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.