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

0:0.06

1:0.07

2:0.09

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

idia

-1.95

icum

-1.91

inian

-1.89

 Artemis

-1.84

mite

-1.84

tered

-1.78

athi

-1.75

arin

-1.75

gaard

-1.74

 Herod

-1.71

POSITIVE LOGITS

 rall

2.17

Discuss

2.10

将

1.97

 Leilan

1.91

 basics

1.86

 Mens

1.82

 embr

1.81

 undermin

1.79

selves

1.75

 fundament

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.