INDEX

Explanations

the word "with."

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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

 mush

-2.69

 Kafka

-2.60

Yug

-2.55

 Kurd

-2.52

ravel

-2.52

sob

-2.48

�

-2.47

OPLE

-2.44

wa

-2.44

 slideshow

-2.42

POSITIVE LOGITS

 Lethal

2.75

cial

2.73

rontal

2.69

 Flavoring

2.62

 Colonial

2.57

MLG

2.45

ortal

2.45

ethyl

2.44

ames

2.42

CM

2.40

Activations Density 0.000%

the word "with."

No Comments

No Known Activations