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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 cele

-1.68

 Collection

-1.56

 Stats

-1.53

oa

-1.51

TMZ

-1.51

 Incarnation

-1.49

 Wiki

-1.49

 Tune

-1.47

 Runtime

-1.47

FAQ

-1.46

POSITIVE LOGITS

aeda

1.66

bered

1.61

ledged

1.61

quit

1.55

iably

1.55

ered

1.55

Pand

1.53

 Monsanto

1.53

luaj

1.52

ornia

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.