INDEX

Explanations

references to basketball drafts and player selections

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.01

1:0.01

2:0.08

3:0.05

4:0.10

5:0.02

6:0.02

7:0.41

8:0.02

9:0.03

10:0.14

11:0.07

Negative Logits

 coping

-1.72

 routines

-1.68

 frustrations

-1.63

 responsiveness

-1.61

eat

-1.60

 effectiveness

-1.60

Relations

-1.59

 neglect

-1.59

 failings

-1.58

 impunity

-1.58

POSITIVE LOGITS

*/(

1.69

 ballots

1.67

 lottery

1.64

 eligible

1.61

 Grayson

1.61

 ballot

1.58

 Selected

1.56

 Yuri

1.55

 Salary

1.54

Activations Density 0.013%

references to basketball drafts and player selections

No Comments

No Known Activations