INDEX

Explanations

past tense verbs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

0:0.07

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.09

Negative Logits

abeth

-1.80

mson

-1.75

aples

-1.69

agements

-1.66

RFC

-1.61

fest

-1.60

assetsadobe

-1.59

own

-1.59

arettes

-1.56

brance

-1.53

POSITIVE LOGITS

 investigator

1.76

 Investigative

1.71

 investigative

1.57

 Virus

1.56

 Inspector

1.45

 virus

1.44

 Prosecutor

1.44

Jem

1.43

CRC

1.42

 Genius

1.42

Activations Density 0.000%

past tense verbs

No Comments

No Known Activations