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

0:0.09

1:0.08

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.08

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

inia

-1.81

agascar

-1.77

��

-1.58

 Desert

-1.49

 Cosponsors

-1.49

insula

-1.48

obia

-1.46

���

-1.46

illo

-1.46

 Lust

-1.46

POSITIVE LOGITS

steen

1.85

ware

1.60

merce

1.57

 techno

1.56

 multiplication

1.53

Ctrl

1.49

dB

1.46

antry

1.45

anke

1.45

bda

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.