INDEX

Explanations

instances of spitting or related actions in various contexts

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

1:0.02

2:0.08

3:0.13

4:0.01

5:0.03

6:0.07

7:0.15

8:0.06

9:0.20

10:0.07

11:0.11

Negative Logits

Quantity

-1.22

 tradem

-1.18

Availability

-1.14

vernment

-1.13

widget

-1.11

illac

-1.07

 GOODMAN

-1.07

Measure

-1.06

Label

-1.06

INO

-1.05

POSITIVE LOGITS

upon

1.35

 uncontroll

1.26

 helpless

1.18

 venom

1.09

 inco

1.07

opian

1.07

 furiously

1.06

 useless

1.05

 nause

1.05

hus

1.04

Activations Density 0.005%

instances of spitting or related actions in various contexts

No Comments

No Known Activations