INDEX

Explanations

phrases related to courage and personal challenges

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

0:0.07

1:0.03

2:0.28

3:0.12

4:0.04

5:0.09

6:0.05

7:0.07

8:0.03

9:0.05

10:0.06

11:0.03

Negative Logits

installed

-2.60

Rot

-2.59

 visitation

-2.49

 MIDI

-2.46

 subdiv

-2.43

 sorted

-2.42

Brow

-2.40

 scheduling

-2.40

 Merge

-2.39

 overlap

-2.39

POSITIVE LOGITS

 courage

6.42

 bravery

6.25

 courageous

5.55

 Courage

5.21

 coward

5.14

 fearless

4.98

 heroism

4.62

 persever

4.58

 brave

4.57

 humility

4.55

Activations Density 0.192%

phrases related to courage and personal challenges

No Comments

No Known Activations