INDEX

Explanations

quantitative relationships and probabilities related to hypotheses and evidence

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.15

1:0.11

2:0.08

3:0.07

4:0.06

5:0.06

6:0.08

7:0.13

8:0.05

9:0.04

10:0.08

11:0.04

Negative Logits

 Shak

-3.20

leasing

-2.60

 Ches

-2.58

 Kendrick

-2.49

 GOODMAN

-2.46

Lon

-2.45

 Chero

-2.43

 Greenwood

-2.40

 Reeves

-2.38

 Shawn

-2.38

POSITIVE LOGITS

�

3.42

μ

3.23

�

3.14

ェ

2.89

β

2.70

 Kirin

2.69

μ

2.68

wic

2.67

omorphic

2.66

otype

2.58

Activations Density 0.000%

quantitative relationships and probabilities related to hypotheses and evidence

No Comments

No Known Activations