INDEX

Explanations

references to events or occurrences that imply a sequence of actions or conditions

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

0:0.01

1:0.06

2:0.07

3:0.03

4:0.01

5:0.07

6:0.05

7:0.05

8:0.10

9:0.14

10:0.10

11:0.26

Negative Logits

 srfAttach

-1.19

 Calculator

-1.16

idon

-1.09

 antioxid

-1.06

��

-1.05

 Municip

-1.05

 Sending

-1.05

░░

-1.04

\\\\\\\\

-1.02

LIB

-1.02

POSITIVE LOGITS

 cryptoc

1.31

inge

1.25

ospace

1.25

ukong

1.25

luster

1.23

wcs

1.19

adelphia

1.17

improve

1.16

osc

1.16

apse

1.15

Activations Density 0.017%

references to events or occurrences that imply a sequence of actions or conditions

No Comments

No Known Activations