INDEX

Explanations

terms indicating size or magnitude in various contexts

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.11

1:0.02

2:0.16

3:0.17

4:0.05

5:0.08

6:0.02

7:0.01

8:0.08

9:0.17

10:0.05

11:0.02

Negative Logits

��

-1.45

��

-1.31

ribly

-1.21

 Jenkins

-1.17

matically

-1.17

 banter

-1.15

 Jord

-1.13

 Kaufman

-1.11

enko

-1.11

 Jacques

-1.11

POSITIVE LOGITS

 imaginable

1.44

occup

1.41

iameter

1.39

Union

1.32

(>

1.31

leground

1.26

agu

1.25

largest

1.23

Ever

1.23

abal

1.20

Activations Density 0.043%

terms indicating size or magnitude in various contexts

No Comments

No Known Activations