INDEX

Explanations

instances of the character 'Ċ'

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.10

1:0.05

2:0.09

3:0.08

4:0.09

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

aspers

-1.86

 ling

-1.75

 Cher

-1.64

 Ashe

-1.59

jri

-1.58

ilic

-1.55

ypes

-1.51

acea

-1.50

gypt

-1.50

udic

-1.49

POSITIVE LOGITS

ISO

2.30

 airs

1.93

ISO

1.88

Exit

1.71

upload

1.65

lvl

1.64

Disk

1.62

framework

1.61

rar

1.60

budget

1.58

Activations Density 0.000%

instances of the character 'Ċ'

No Comments

No Known Activations