INDEX

Explanations

references to academic departments and institutions

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

3:0.07

4:0.10

5:0.02

6:0.05

7:0.39

8:0.03

9:0.03

10:0.08

11:0.07

Negative Logits

 defiant

-1.82

 confidently

-1.68

 attest

-1.64

 unsus

-1.62

ItemImage

-1.60

 brazen

-1.60

 leaps

-1.59

�

-1.54

ewitness

-1.52

 unequivocally

-1.49

POSITIVE LOGITS

 Management

1.79

 Consolid

1.76

 Maintenance

1.72

 Nutrition

1.72

 upkeep

1.70

 Design

1.69

HUD

1.68

 Arts

1.66

 Agriculture

1.61

 Journalism

1.61

Activations Density 0.017%

references to academic departments and institutions

No Comments

No Known Activations