INDEX

Explanations

keywords related to changes in conditions or situations, especially regarding statistics or reports

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

0:0.05

1:0.11

2:0.03

3:0.05

4:0.04

5:0.03

6:0.07

7:0.41

8:0.02

9:0.03

10:0.03

11:0.06

Negative Logits

 delet

-2.83

Dup

-2.77

 deletion

-2.72

 deleted

-2.72

 deleting

-2.59

 retracted

-2.43

 dots

-2.41

 layoffs

-2.40

Letter

-2.39

 retreating

-2.37

POSITIVE LOGITS

oS

2.94

hus

2.76

avascript

2.72

 Skydragon

2.71

Thom

2.71

 Seym

2.69

SourceFile

2.64

HC

2.53

NXT

2.53

ITV

2.53

Activations Density 0.001%

keywords related to changes in conditions or situations, especially regarding statistics or reports

No Comments

No Known Activations