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

0:0.07

1:0.12

2:0.08

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Carbuncle

-2.26

QC

-1.68

 Quantum

-1.68

 catalog

-1.59

cog

-1.55

 speculate

-1.51

velength

-1.51

 Seeds

-1.51

 pond

-1.49

 Carrier

-1.49

POSITIVE LOGITS

yth

1.98

ADRA

1.91

ocent

1.71

amar

1.70

 autonomy

1.69

elo

1.64

wake

1.59

eah

1.58

DEP

1.57

HOU

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.