INDEX

Explanations

expressions related to self-harm and suicide

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

1:0.02

2:0.09

3:0.09

4:0.02

5:0.03

6:0.05

7:0.10

8:0.16

9:0.17

10:0.05

11:0.13

Negative Logits

taboola

-1.32

glers

-1.27

 Presents

-1.23

ciplinary

-1.22

CLUD

-1.15

published

-1.12

lished

-1.08

spect

-1.06

══

-1.05

Statement

-1.03

POSITIVE LOGITS

 chunk

1.15

 unborn

1.15

 invaders

1.10

ego

1.08

 damn

1.08

dro

1.06

 crap

1.06

 shit

1.05

 pesky

1.04

 goddamn

1.03

Activations Density 0.042%

expressions related to self-harm and suicide

No Comments

No Known Activations