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

Head Attr Weights

0:0.07

1:0.06

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.10

10:0.08

11:0.08

Negative Logits

 prosec

-1.50

 suspic

-1.44

 poaching

-1.44

film

-1.42

]}

-1.40

 challeng

-1.39

 Steele

-1.39

));

-1.38

 veto

-1.35

 splash

-1.34

POSITIVE LOGITS

ournals

1.81

ynchronous

1.74

phia

1.66

igslist

1.66

Fif

1.56

DIT

1.56

XT

1.54

pill

1.54

ixt

1.54

oaded

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.