INDEX

Explanations

occurrences of the word "can" and its various forms

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.04

2:0.08

3:0.05

4:0.03

5:0.05

6:0.09

7:0.06

8:0.16

9:0.06

10:0.17

11:0.07

Negative Logits

 Conan

-1.04

 Horowitz

-0.95

ei

-0.95

iban

-0.95

 Fitz

-0.94

 Rack

-0.88

�

-0.88

 Verse

-0.87

 Spear

-0.86

Uni

-0.85

POSITIVE LOGITS

 safely

1.34

mbuds

1.29

 confidently

1.29

 freely

1.03

ustomed

1.02

uate

1.02

imens

0.99

��

0.98

 cultivate

0.97

umsy

0.96

Activations Density 0.221%

occurrences of the word "can" and its various forms

No Comments

No Known Activations