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

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

=(

-3.20

Syd

-3.06

EEE

-2.74

 Communists

-2.70

 USSR

-2.69

+=

-2.68

((

-2.66

 prolet

-2.63

 almonds

-2.61

 Nazis

-2.59

POSITIVE LOGITS

 lantern

3.04

 vantage

2.71

dayName

2.68

ajor

2.66

 Thorn

2.61

Frames

2.61

 muzzle

2.53

Fram

2.51

 puck

2.47

Ori

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.