INDEX

Explanations

proper nouns and specific locations or entities

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.04

1:0.06

2:0.09

3:0.03

4:0.02

5:0.02

6:0.06

7:0.04

8:0.02

9:0.03

10:0.50

11:0.03

Negative Logits

ACY

-2.47

awed

-2.32

ACA

-2.23

ctor

-2.18

ESCO

-2.15

ザ

-2.14

cha

-2.14

avin

-2.11

cone

-2.11

 therap

-2.07

POSITIVE LOGITS

LT

3.64

LT

3.30

Lum

3.30

Lux

3.14

3.11

LX

3.08

Louis

3.00

LL

2.98

LR

2.96

LU

2.95

Activations Density 0.059%

proper nouns and specific locations or entities

No Comments

No Known Activations