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

0:0.09

1:0.05

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.09

10:0.09

11:0.08

Negative Logits

ignt

-1.66

anchester

-1.55

 Winds

-1.53

ECB

-1.52

itutes

-1.47

ebted

-1.47

 Cipher

-1.40

escription

-1.40

 ASCII

-1.40

ultane

-1.36

POSITIVE LOGITS

etimes

1.44

 Member

1.43

Member

1.43

ndra

1.42

obiles

1.42

 vape

1.41

thing

1.41

 vaping

1.40

aah

1.39

 experien

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.