INDEX

Explanations

No Explanations Found

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

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.10

10:0.08

11:0.07

Negative Logits

CG

-3.07

BG

-2.84

staking

-2.80

BG

-2.73

 Dive

-2.72

IPM

-2.69

 Alchemist

-2.67

Gou

-2.57

[*

-2.56

urdue

-2.55

POSITIVE LOGITS

 paran

2.85

 Wilhelm

2.57

 pardon

2.56

 decency

2.54

eteenth

2.47

 eras

2.44

 Watt

2.44

 pity

2.44

 ageing

2.44

 manners

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.