INDEX

Explanations

references to specific religious practices

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

0:0.07

1:0.08

2:0.07

3:0.09

4:0.09

5:0.08

6:0.10

7:0.08

8:0.06

9:0.08

10:0.07

11:0.08

Negative Logits

Education

-3.15

��

-2.91

funding

-2.87

bilt

-2.85

ALK

-2.84

AH

-2.79

‎

-2.78

cephal

-2.75

Corn

-2.74

ForgeModLoader

-2.70

POSITIVE LOGITS

 simultane

2.91

FN

2.89

dye

2.76

 snail

2.74

 pubs

2.72

 tavern

2.72

 torpedo

2.70

 Skydragon

2.69

 squid

2.66

 vodka

2.64

Activations Density 0.000%

references to specific religious practices

No Comments

No Known Activations