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

1:0.07

2:0.08

3:0.08

4:0.09

5:0.09

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

inventoryQuantity

-3.17

_-

-3.12

ICE

-3.02

Percent

-2.99

aez

-2.92

Cache

-2.90

Aff

-2.83

overty

-2.80

eger

-2.79

iHUD

-2.76

POSITIVE LOGITS

 spectator

2.83

 Monarch

2.58

 complete

2.56

 Royal

2.55

 promoter

2.55

Jur

2.48

 Rothschild

2.41

 Construct

2.40

 machinery

2.38

 downstream

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.