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

1:0.06

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

ーティ

-2.73

 giveaway

-2.65

 divest

-2.64

boo

-2.60

 newsletter

-2.56

 brist

-2.55

 rave

-2.47

 Carbuncle

-2.39

 newsletters

-2.35

 Keynes

-2.31

POSITIVE LOGITS

 Trace

2.96

................................

2.92

........................

2.83

DN

2.82

ERT

2.77

"},{"

2.68

..................

2.66

":{"

2.58

 Colony

2.46

Sec

2.37

Activations Density 0.000%

references to the Quran

No Comments

No Known Activations