INDEX

Explanations

emphasized singular concepts or important elements in a narrative

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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

vr

-2.80

','

-2.56

GREEN

-2.49

TN

-2.45

react

-2.42

enzie

-2.41

eka

-2.35

liest

-2.34

 realised

-2.33

 mutated

-2.31

POSITIVE LOGITS

 Fountain

2.68

amas

2.58

 Panc

2.53

 Bahrain

2.51

Bah

2.49

POST

2.47

jas

2.35

 Nicarag

2.32

 fountain

2.31

Mig

2.27

Activations Density 0.000%

emphasized singular concepts or important elements in a narrative

No Comments

No Known Activations