INDEX

Explanations

the word "to."

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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.07

5:0.08

6:0.10

7:0.09

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Genius

-2.98

 Pont

-2.90

 Crim

-2.89

Pont

-2.87

 Fasc

-2.71

 Dinosaur

-2.64

Ada

-2.59

 Alexander

-2.56

Au

-2.56

 Mutant

-2.55

POSITIVE LOGITS

ayne

3.73

wcs

3.49

izen

2.81

dule

2.77

cember

2.75

orea

2.69

soDeliveryDate

2.68

rys

2.66

essel

2.62

range

2.58

Activations Density 0.000%

the word "to."

No Comments

No Known Activations