INDEX

Explanations

symbols or characters associated with encoding or representation

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.02

2:0.05

3:0.07

4:0.04

5:0.03

6:0.44

7:0.07

8:0.04

9:0.05

10:0.07

11:0.04

Negative Logits

 biodiversity

-1.46

 bushes

-1.44

 avoidance

-1.36

 offence

-1.33

ividual

-1.33

 agitation

-1.32

 corpus

-1.29

 independ

-1.28

 traffic

-1.25

 diffusion

-1.23

POSITIVE LOGITS

�

1.95

�

1.87

�

1.83

�

1.82

�

1.82

士

1.80

�

1.78

�

1.75

�

1.74

�

1.73

Activations Density 0.003%

symbols or characters associated with encoding or representation

No Comments

No Known Activations