INDEX

Explanations

phrases indicating potential actions or procedures

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

1:0.03

2:0.11

3:0.19

4:0.01

5:0.02

6:0.05

7:0.05

8:0.06

9:0.18

10:0.08

11:0.13

Negative Logits

hess

-1.13

ornia

-1.11

 Rowe

-1.09

URE

-1.08

YN

-1.04

oggle

-1.03

Tub

-1.00

encer

-0.96

LM

-0.95

Riv

-0.95

POSITIVE LOGITS

soType

1.23

aneously

1.12

origin

1.09

gp

1.06

catentry

1.04

actionDate

1.03

anus

1.01

phrine

1.00

devices

0.97

obyl

0.96

Activations Density 0.018%

phrases indicating potential actions or procedures

No Comments

No Known Activations