INDEX

Explanations

actions related to searching and discovering information

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

0:0.02

1:0.01

2:0.05

3:0.06

4:0.05

5:0.08

6:0.02

7:0.05

8:0.06

9:0.08

10:0.36

11:0.11

Negative Logits

 veto

-1.95

 dominates

-1.73

 embodies

-1.71

 dominating

-1.64

 Marketable

-1.56

zbollah

-1.55

 precedence

-1.44

 Franchise

-1.43

iri

-1.42

regulation

-1.41

POSITIVE LOGITS

 uncover

2.03

earchers

1.97

 Investigator

1.92

Scan

1.81

 conclud

1.80

 investigator

1.78

Finding

1.78

��

1.76

 scanning

1.75

 probing

1.75

Activations Density 0.579%

actions related to searching and discovering information

No Comments

No Known Activations