INDEX

Explanations

actions related to initiation or engagement in various activities

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

2:0.24

3:0.03

4:0.01

5:0.03

6:0.04

7:0.05

8:0.12

9:0.11

10:0.07

11:0.17

Negative Logits

Downloadha

-1.19

 delight

-1.10

 neglig

-1.08

 discarded

-1.04

 abandoned

-0.99

 proverb

-0.97

 exclaim

-0.97

 Brach

-0.97

 obtained

-0.96

 unfit

-0.96

POSITIVE LOGITS

HER

1.27

sburgh

1.26

 ACTIONS

1.11

ASS

1.11

asso

1.10

THING

1.10

thumbnails

1.09

────

1.08

 tomorrow

1.07

hing

1.06

Activations Density 0.029%

actions related to initiation or engagement in various activities

No Comments

No Known Activations