INDEX

Explanations

references to government or official settings

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

く

-2.77

edo

-2.76

bourg

-2.69

een

-2.67

hyde

-2.67

�

-2.61

}}}

-2.57

etsy

-2.57

ecause

-2.56

gil

-2.54

POSITIVE LOGITS

Ivy

2.93

 POWER

2.67

Kah

2.67

Vog

2.49

pour

2.44

 Roundup

2.43

 Hers

2.40

 Gors

2.33

 Abbott

2.32

BDS

2.29

Activations Density 0.000%

references to government or official settings

No Comments

No Known Activations