INDEX

Explanations

names of people and places, particularly in the context of significant events or actions

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

0:0.02

1:0.03

2:0.10

3:0.29

4:0.02

5:0.02

6:0.13

7:0.08

8:0.06

9:0.08

10:0.07

11:0.07

Negative Logits

usterity

-1.18

 manure

-1.05

ドラゴン

-1.03

 Impossible

-0.96

 Yugoslav

-0.96

alysis

-0.95

 diaper

-0.95

 disgrace

-0.93

 consolidation

-0.93

 Dirt

-0.92

POSITIVE LOGITS

�醒

1.26

ayn

1.24

Hour

1.21

angan

1.15

croft

1.14

aina

1.12

rity

1.12

Introduced

1.10

onga

1.09

schild

1.08

Activations Density 0.004%

names of people and places, particularly in the context of significant events or actions

No Comments

No Known Activations