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

0:0.09

1:0.06

2:0.09

3:0.10

4:0.09

5:0.06

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

ookie

-1.61

assis

-1.50

ESA

-1.49

 Exclusive

-1.44

leeve

-1.42

hare

-1.38

 buyer

-1.37

DoS

-1.36

 Crypto

-1.33

 Email

-1.33

POSITIVE LOGITS

etics

1.82

ischer

1.63

 inefficient

1.59

 ineffective

1.46

 habitual

1.40

iferation

1.39

 sluggish

1.37

 Trib

1.36

heastern

1.35

 fatig

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.