INDEX

Explanations

terms related to the assessment of performance or evaluation

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

0:0.03

1:0.03

2:0.08

3:0.31

4:0.03

5:0.02

6:0.13

7:0.08

8:0.06

9:0.06

10:0.08

11:0.04

Negative Logits

�

-1.30

�

-1.23

 sugg

-1.23

achus

-1.20

yip

-1.19

ulum

-1.18

govtrack

-1.17

Friends

-1.13

enance

-1.13

States

-1.10

POSITIVE LOGITS

 Malfoy

1.18

 Misty

1.06

ministic

0.98

 Orig

0.98

 goblin

0.97

LSD

0.93

 Audi

0.93

dit

0.93

tarian

0.92

 encyclopedia

0.92

Activations Density 0.009%

terms related to the assessment of performance or evaluation

No Comments

No Known Activations