INDEX

Explanations

specific types of comments and formatting indicators in text

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.35

1:0.15

2:0.04

3:0.03

4:0.02

5:0.07

6:0.03

7:0.01

8:0.08

9:0.08

10:0.05

11:0.03

Negative Logits

ogun

-1.79

zbek

-1.79

gebra

-1.78

ğ

-1.74

ajor

-1.74

miah

-1.70

assic

-1.54

jriwal

-1.52

jri

-1.52

actor

-1.52

POSITIVE LOGITS

DIS

2.92

 CONS

2.81

HY

2.59

ACC

2.59

SU

2.53

PET

2.52

DET

2.52

SUP

2.51

 THANK

2.45

USE

2.45

Activations Density 0.095%

specific types of comments and formatting indicators in text

No Comments

No Known Activations