INDEX

Explanations

phrases that indicate signals or indications of actions or decisions

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

New Auto-Interp

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

1:0.00

2:0.04

3:0.05

4:0.12

5:0.02

6:0.10

7:0.37

8:0.02

9:0.03

10:0.10

11:0.08

Negative Logits

 Candy

-1.43

anon

-1.38

von

-1.38

 Byzantine

-1.36

 Basil

-1.34

 Malaysia

-1.28

 Mansion

-1.27

 Anat

-1.25

 Ferr

-1.25

 Salman

-1.25

POSITIVE LOGITS

 signals

1.83

 signal

1.81

intent

1.72

sign

1.65

 intent

1.63

positive

1.58

 impending

1.55

stop

1.53

trl

1.47

IFF

1.45

Activations Density 0.009%

phrases that indicate signals or indications of actions or decisions

No Comments

No Known Activations