INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.07

2:0.09

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

enegger

-2.10

Nug

-1.84

"@

-1.75

 scalp

-1.71

daq

-1.69

 nasal

-1.51

 meets

-1.50

 Jenner

-1.48

 Huntington

-1.47

 antiv

-1.47

POSITIVE LOGITS

ami

1.70

 arrang

1.61

��

1.56

eria

1.50

tera

1.50

κ

1.50

 maths

1.46

shed

1.44

artifacts

1.43

visible

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.