INDEX

Explanations

references to the Quran

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

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.09

7:0.06

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 CARD

-2.94

 Tall

-2.73

Ct

-2.70

 Pall

-2.65

ttes

-2.63

lou

-2.62

 Introduced

-2.59

olas

-2.58

 Wolfgang

-2.51

 refill

-2.48

POSITIVE LOGITS

casts

2.91

 Dalai

2.91

CIA

2.90

 Tibet

2.69

 stereotype

2.67

 coding

2.52

 stereotypes

2.50

camp

2.50

furt

2.49

 reincarn

2.48

Activations Density 0.000%

references to the Quran

No Comments

No Known Activations