INDEX

Explanations

phrases related to struggles with personal choices and societal issues

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.06

1:0.02

2:0.10

3:0.12

4:0.06

5:0.13

6:0.02

7:0.32

8:0.03

9:0.01

10:0.05

11:0.03

Negative Logits

ubb

-2.27

ftime

-2.08

erial

-2.07

actly

-1.97

ebus

-1.96

rul

-1.95

orney

-1.93

astern

-1.90

icus

-1.90

ichick

-1.89

POSITIVE LOGITS

their

5.32

 their

5.04

Their

4.51

 THEIR

4.44

 themselves

4.39

 theirs

4.31

 Their

4.21

 they

3.89

They

3.89

they

3.84

Activations Density 1.449%

phrases related to struggles with personal choices and societal issues

No Comments

No Known Activations