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

2:0.08

3:0.07

4:0.10

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

Whe

-2.68

zai

-2.67

 Horowitz

-2.60

Osw

-2.54

Si

-2.46

Zac

-2.41

 Zone

-2.40

 Element

-2.37

 McKenzie

-2.35

alez

-2.34

POSITIVE LOGITS

ftime

3.18

oult

2.85

 replen

2.75

renheit

2.72

mson

2.70

ashington

2.69

Downloadha

2.62

2.57

 hurricanes

2.56

 deval

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.