INDEX

Explanations

the use of personal pronouns

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ゴン

-2.93

�醒

-2.75

 lett

-2.71

 beads

-2.68

 Mono

-2.65

 sqor

-2.63

AAAA

-2.60

ectar

-2.50

AUD

-2.49

 absorb

-2.40

POSITIVE LOGITS

Putin

3.55

 Petraeus

3.39

oshenko

3.30

 Putin

3.26

 Ukrainians

3.02

andowski

3.02

Naz

2.92

 Kremlin

2.90

chwitz

2.88

oslav

2.86

Activations Density 0.000%

the use of personal pronouns

No Comments

No Known Activations