INDEX

Explanations

references to censorship or content removal

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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.10

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

renheit

-2.88

uberty

-2.85

 Bella

-2.85

imaru

-2.80

Child

-2.80

 pornographic

-2.74

 nude

-2.74

 scriptures

-2.67

 Revelations

-2.64

 sexually

-2.60

POSITIVE LOGITS

 stabilization

2.70

gran

2.64

 dynam

2.62

spection

2.58

 rebuilding

2.52

 salvage

2.46

 warranty

2.41

 Merc

2.38

 rebuild

2.35

ogether

2.33

Activations Density 0.000%

references to censorship or content removal

No Comments

No Known Activations