INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.10

6:0.07

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 mamm

-1.65

 transpl

-1.62

mos

-1.61

 guarding

-1.60

 decoration

-1.59

 advoc

-1.56

 watering

-1.53

warts

-1.53

advertising

-1.50

 rooting

-1.49

POSITIVE LOGITS

SPONSORED

1.87

chio

1.83

 Beginning

1.65

Spell

1.61

Machine

1.60

 Participant

1.59

Pause

1.52

ajo

1.50

dule

1.50

Beginning

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.