INDEX

Explanations

information related to account management and changes in public testing environments

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

0:0.09

1:0.02

2:0.05

3:0.17

4:0.05

5:0.11

6:0.02

7:0.12

8:0.04

9:0.02

10:0.21

11:0.04

Negative Logits

 dared

-2.27

 paralyzed

-2.11

 crippled

-2.05

 cumbers

-1.90

 stranded

-1.85

 defied

-1.82

 feared

-1.81

 convict

-1.77

 violated

-1.77

 arrogance

-1.75

POSITIVE LOGITS

 updates

3.46

 Updates

3.28

 update

3.09

 periodically

2.69

 announcements

2.69

 Update

2.69

 updated

2.58

 newsletter

2.53

 updating

2.52

 accordingly

2.47

Activations Density 0.262%

information related to account management and changes in public testing environments

No Comments

No Known Activations