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

0:0.07

1:0.06

2:0.07

3:0.09

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.10

Negative Logits

tf

-1.72

livion

-1.57

illin

-1.53

inho

-1.51

notations

-1.46

 shelves

-1.46

 Runes

-1.45

 folders

-1.45

uel

-1.42

 strings

-1.38

POSITIVE LOGITS

 millenn

1.77

 behavi

1.73

GoldMagikarp

1.67

 advoc

1.60

 convers

1.58

ospons

1.56

 Surviv

1.55

 causation

1.54

ariat

1.54

 Unch

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.