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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

 unsuccessful

-1.88

 Contra

-1.75

iculty

-1.66

 agitation

-1.66

 lobb

-1.65

 Moral

-1.64

lag

-1.58

 criminally

-1.56

bestos

-1.56

 disbelief

-1.56

POSITIVE LOGITS

dra

2.05

aez

2.03

ibles

1.97

�

1.80

acy

1.80

ANN

1.78

itely

1.78

content

1.77

umbnails

1.74

cients

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.