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

1:0.04

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.10

10:0.08

11:0.08

Negative Logits

 moons

-1.77

 centuries

-1.75

othal

-1.65

 plutonium

-1.61

ortality

-1.57

 disinteg

-1.57

clair

-1.55

chnology

-1.55

 shelves

-1.55

livion

-1.54

POSITIVE LOGITS

":""},{"

1.73

hess

1.65

cript

1.64

omen

1.60

Friend

1.59

ESE

1.56

imon

1.56

 Kaiser

1.55

HA

1.54

avoid

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.