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

2:0.09

3:0.08

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.08

10:0.06

11:0.08

Negative Logits

 tink

-2.11

 Investigator

-1.89

 myst

-1.89

 cred

-1.85

 predicting

-1.85

 tossing

-1.80

 jurisdiction

-1.80

 patience

-1.80

 nerds

-1.79

 superst

-1.77

POSITIVE LOGITS

folios

2.37

azel

2.26

igrated

2.23

accompanied

2.17

ocaust

2.13

 Flavoring

2.13

igrate

2.12

pread

2.12

yne

2.06

ohydrate

2.02

Activations Density 0.000%

No Known Activations

This feature has no known activations.