INDEX

Explanations

terms related to project management and process improvement

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

1:0.03

2:0.10

3:0.12

4:0.12

5:0.14

6:0.02

7:0.19

8:0.04

9:0.02

10:0.06

11:0.03

Negative Logits

pse

-2.12

 disgr

-1.96

 mans

-1.95

indal

-1.90

 prostitute

-1.87

 bearer

-1.85

�

-1.85

 incest

-1.82

 foreigner

-1.81

tein

-1.79

POSITIVE LOGITS

 ourselves

4.04

our

3.29

Our

3.14

We

3.10

We

2.80

we

2.75

we

2.74

Our

2.60

 ours

2.39

us

2.33

Activations Density 0.483%

terms related to project management and process improvement

No Comments

No Known Activations