INDEX

Explanations

specific measurements and weights

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

0:0.12

1:0.02

2:0.10

3:0.18

4:0.03

5:0.19

6:0.02

7:0.07

8:0.04

9:0.02

10:0.14

11:0.02

Negative Logits

 lanes

-2.03

 Opportun

-1.92

 unemployment

-1.83

 loophole

-1.80

 lane

-1.77

STATE

-1.77

 congest

-1.76

 unchecked

-1.74

ゼウス

-1.73

 paths

-1.70

POSITIVE LOGITS

merce

2.02

odies

1.94

ansky

1.93

iewicz

1.90

 weigh

1.89

Gul

1.89

pees

1.88

TNT

1.86

ogy

1.85

�士

1.81

Activations Density 0.027%

specific measurements and weights

No Comments

No Known Activations