INDEX

Explanations

references to individuals or personal pronouns indicating presence or participation

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.09

6:0.09

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

onga

-2.88

RC

-2.81

CV

-2.75

RV

-2.71

Clar

-2.68

+)

-2.67

Ross

-2.65

TN

-2.64

ggies

-2.54

 Vaughan

-2.53

POSITIVE LOGITS

 Sorce

3.02

 assassins

2.66

 Bungie

2.59

 Masquerade

2.59

 comet

2.58

 mete

2.54

utsche

2.49

aspers

2.49

wolves

2.44

 Comet

2.41

Activations Density 0.000%

references to individuals or personal pronouns indicating presence or participation

No Comments

No Known Activations