INDEX

Explanations

mentions of the X-Men franchise and its characters

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

0:0.06

1:0.03

2:0.04

3:0.06

4:0.06

5:0.05

6:0.02

7:0.08

8:0.02

9:0.31

10:0.12

11:0.11

Negative Logits

 ourselves

-2.95

our

-2.75

 ripe

-2.39

 ours

-2.33

 myself

-2.24

 ransom

-2.23

my

-2.17

we

-2.13

 smell

-2.07

Jol

-2.07

POSITIVE LOGITS

rays

2.61

itely

2.55

anos

2.50

quished

2.45

monster

2.43

 mutants

2.39

iners

2.35

wolves

2.31

lisher

2.30

rawler

2.30

Activations Density 0.002%

mentions of the X-Men franchise and its characters

No Comments

No Known Activations