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

0:0.09

1:0.08

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 generously

-1.79

awa

-1.78

 oils

-1.61

 illegally

-1.57

 desperately

-1.56

 apologise

-1.54

ana

-1.54

 evac

-1.54

 Alic

-1.54

yss

-1.53

POSITIVE LOGITS

ーテ

1.64

Parameters

1.61

ategories

1.59

arten

1.56

idence

1.56

 Hallow

1.55

ranean

1.55

 unfocusedRange

1.54

().

1.54

uted

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.