INDEX

Explanations

words indicating connections or relationships in the context of information flow or industry standards

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

0:0.08

1:0.08

2:0.06

3:0.09

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 patron

-2.77

 imperson

-2.72

 proletarian

-2.71

 Muss

-2.69

mot

-2.56

 Bour

-2.56

hun

-2.52

 Kaufman

-2.47

 Twain

-2.40

 Lyndon

-2.40

POSITIVE LOGITS

ㅋㅋ

3.25

YP

3.13

ertodd

3.06

��

3.03

�

3.00

Enlarge

3.00

CPU

2.99

zik

2.99

 XCOM

2.93

�

2.87

Activations Density 0.000%

words indicating connections or relationships in the context of information flow or industry standards

No Comments

No Known Activations