INDEX

Explanations

No Explanations Found

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

0:0.07

1:0.07

2:0.09

3:0.09

4:0.09

5:0.07

6:0.07

7:0.09

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

thood

-3.30

nep

-2.84

 concess

-2.77

(*

-2.75

 paed

-2.73

dates

-2.67

 lear

-2.66

verty

-2.62

 mould

-2.59

POSITIVE LOGITS

Gas

3.29

 Bass

3.12

 demolished

2.94

 barric

2.93

 demol

2.93

 demolition

2.83

 Drag

2.80

 Stern

2.80

 Silva

2.78

 Strip

2.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.