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

0:0.08

1:0.05

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 =====

-1.84

 Hurt

-1.81

Ok

-1.79

 Glass

-1.76

IU

-1.75

acebook

-1.74

akeru

-1.74

 Survey

-1.65

 Asuka

-1.59

Lak

-1.57

POSITIVE LOGITS

 euphem

2.08

Timeout

2.00

wra

1.97

 chained

1.93

�

1.89

alias

1.74

fetched

1.74

ext

1.74

prefix

1.73

necess

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.