INDEX

Explanations

phrases indicating proximity or boundaries

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

0:0.01

1:0.02

2:0.05

3:0.34

4:0.01

5:0.02

6:0.06

7:0.12

8:0.05

9:0.05

10:0.08

11:0.15

Negative Logits

 subordinate

-1.18

‎

-1.16

RIP

-1.14

ufact

-1.13

elfare

-1.11

 entrusted

-1.10

onse

-1.07

urdue

-1.06

emphasis

-1.05

coni

-1.04

POSITIVE LOGITS

 wedge

1.29

aceous

1.22

 Dull

1.11

 diced

1.10

 Judgment

1.09

Rect

1.08

amiya

1.07

 veins

1.07

 scor

1.05

erest

1.04

Activations Density 0.007%

phrases indicating proximity or boundaries

No Comments

No Known Activations