INDEX

Explanations

occurrences of specific nouns and phrases in a document

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

0:0.05

1:0.09

2:0.03

3:0.10

4:0.08

5:0.05

6:0.04

7:0.34

8:0.03

9:0.04

10:0.05

11:0.04

Negative Logits

itans

-3.02

ega

-2.69

■

-2.28

unes

-2.19

lic

-2.19

 Benz

-2.15

[/

-2.15

gs

-2.13

eva

-2.13

olith

-2.13

POSITIVE LOGITS

 second

5.08

second

4.40

Second

4.25

 Second

3.93

 secondly

3.84

Secondly

3.56

 subsequent

3.46

 Secondly

3.12

 third

2.91

 fourth

2.79

Activations Density 0.021%

occurrences of specific nouns and phrases in a document

No Comments

No Known Activations