INDEX

Explanations

instances of punctuation and certain articles or prepositions in the text

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

1:0.13

2:0.10

3:0.05

4:0.02

5:0.02

6:0.06

7:0.11

8:0.02

9:0.04

10:0.18

11:0.06

Negative Logits

Na

-3.59

GSL

-3.01

 Mississ

-3.00

 membrane

-2.97

 membranes

-2.97

tem

-2.94

Na

-2.89

 Miracle

-2.81

ogi

-2.77

Ir

-2.65

POSITIVE LOGITS

 Wald

9.48

wald

4.29

 Kamp

3.94

Sax

3.85

 Gott

3.51

CENT

3.51

Wolf

3.49

Wen

3.49

 Vikings

3.44

Wal

3.41

Activations Density 0.001%

instances of punctuation and certain articles or prepositions in the text

No Comments

No Known Activations