INDEX

Explanations

connections and relationships between elements in a structured context

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

2:0.07

3:0.04

4:0.03

5:0.07

6:0.07

7:0.35

8:0.06

9:0.04

10:0.08

11:0.09

Negative Logits

essors

-1.24

 Rodham

-1.21

ipeg

-1.15

icut

-1.14

heid

-1.13

Reward

-1.11

$$$$

-1.11

 Newsp

-1.09

AFL

-1.06

League

-1.05

POSITIVE LOGITS

istries

1.16

 animate

1.15

エル

1.15

 populate

1.15

 complement

1.14

kus

1.14

akra

1.14

 protr

1.14

 functionality

1.14

Texture

1.13

Activations Density 0.054%

connections and relationships between elements in a structured context

No Comments

No Known Activations