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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

ploy

-1.66

û

-1.64

�

-1.62

iae

-1.61

 Hitch

-1.57

beit

-1.57

iths

-1.52

 greeted

-1.51

raviolet

-1.50

 gloss

-1.49

POSITIVE LOGITS

olester

1.68

LIA

1.66

conserv

1.63

LT

1.63

 responsible

1.62

reason

1.56

Reason

1.53

 incentive

1.51

inas

1.50

FD

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.