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

0:0.08

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.09

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Bulletin

-3.27

 Tape

-2.94

 Signal

-2.90

 regulator

-2.81

 Publishers

-2.77

 Letters

-2.74

 Rounds

-2.68

tot

-2.67

 Transparency

-2.65

 Burr

-2.64

POSITIVE LOGITS

erest

3.55

eport

3.27

enhagen

3.05

Elsa

2.92

aiman

2.91

braska

2.89

anka

2.88

Minnesota

2.88

ocrin

2.74

ouri

2.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.