INDEX

Explanations

phrases indicating a shared perception or commonality among groups

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.05

1:0.04

2:0.08

3:0.13

4:0.06

5:0.12

6:0.05

7:0.18

8:0.05

9:0.04

10:0.11

11:0.04

Negative Logits

Grab

-2.18

Lev

-2.13

�

-2.13

 ling

-1.98

 Helpful

-1.97

 Harmon

-1.97

Mart

-1.95

 afterwards

-1.94

 elsewhere

-1.93

 Judd

-1.90

POSITIVE LOGITS

chwitz

2.84

clerosis

2.37

iasis

2.34

 Conce

2.30

culosis

2.29

ndra

2.18

ipel

2.13

 polarization

2.11

 bicy

2.08

SIZE

2.05

Activations Density 0.000%

phrases indicating a shared perception or commonality among groups

No Comments

No Known Activations