INDEX

Explanations

references to identity or categorization in various contexts

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

0:0.04

1:0.02

2:0.04

3:0.27

4:0.02

5:0.08

6:0.01

7:0.05

8:0.03

9:0.01

10:0.34

11:0.02

Negative Logits

 positively

-2.33

thirds

-2.30

 exceeds

-2.18

onds

-2.17

both

-2.14

particularly

-2.13

successfully

-2.13

 significantly

-2.08

ificantly

-2.04

icably

-2.03

POSITIVE LOGITS

 scrib

2.69

 whim

2.60

 leftover

2.56

 idle

2.55

 filler

2.44

 gossip

2.43

 whims

2.43

 rumor

2.40

 glitch

2.38

 churn

2.30

Activations Density 0.259%

references to identity or categorization in various contexts

No Comments

No Known Activations