INDEX

Explanations

information related to television series and their release details

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

0:0.22

1:0.03

2:0.06

3:0.08

4:0.07

5:0.03

6:0.07

7:0.17

8:0.03

9:0.05

10:0.04

11:0.09

Negative Logits

️

-2.94

�

-2.93

oğ

-2.91

 Dolphin

-2.88

Mek

-2.85

 drums

-2.76

 Saiyan

-2.66

�

-2.62

 Chomsky

-2.61

 bilingual

-2.59

POSITIVE LOGITS

AMC

4.96

 zombie

4.11

 zombies

3.64

 Zombie

3.12

ombie

3.08

 Zombies

2.93

 Buffy

2.91

 Willow

2.89

 Breaking

2.82

 Xander

2.81

Activations Density 0.002%

information related to television series and their release details

No Comments

No Known Activations