INDEX

Explanations

No Explanations Found

New Auto-Interp

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

1:0.09

2:0.08

3:0.06

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.09

10:0.07

11:0.07

Negative Logits

enum

-2.25

MRI

-1.91

usage

-1.87

inka

-1.82

endon

-1.79

CBC

-1.76

arte

-1.66

BIP

-1.66

ociation

-1.65

rough

-1.65

POSITIVE LOGITS

 multit

2.01

 charact

1.87

 clock

1.78

 weap

1.69

 jails

1.66

 pige

1.64

 spac

1.59

 behav

1.59

tim

1.58

 respons

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.