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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.10

5:0.07

6:0.08

7:0.08

8:0.10

9:0.07

10:0.07

11:0.08

Negative Logits

 busted

-1.59

 Berks

-1.58

nas

-1.55

 Neighbor

-1.52

 Squirrel

-1.49

 scalp

-1.47

 snapped

-1.45

Kev

-1.45

BS

-1.43

 nasal

-1.42

POSITIVE LOGITS

Reviewer

2.50

:]

1.99

etus

1.90

VIEW

1.89

view

1.79

llan

1.77

イト

1.69

omo

1.67

edit

1.59

isen

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.