INDEX

Explanations

names of people or places, particularly related to gruesome events or disturbing content

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

linguistic patterns related to rhyming words

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

1:0.04

2:0.07

3:0.31

4:0.02

5:0.02

6:0.12

7:0.07

8:0.04

9:0.07

10:0.07

11:0.08

Negative Logits

SPONSORED

-1.19

ikuman

-1.15

Brave

-1.10

HCR

-1.09

vironment

-1.09

�

-1.08

TPP

-1.07

ケ

-1.06

AMI

-1.06

イト

-1.05

POSITIVE LOGITS

beck

1.33

arb

1.29

ython

1.13

 Berm

1.08

 Bach

1.05

ivari

1.04

xus

1.02

 Kelley

1.01

 Labrador

1.01

lat

1.00

Activations Density 0.007%

names of people or places, particularly related to gruesome events or disturbing content

linguistic patterns related to rhyming words

No Comments

No Known Activations