INDEX

Explanations

No Explanations Found

New Auto-Interp

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

3:0.08

4:0.08

5:0.06

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

Reviewed

-1.75

afa

-1.67

gaard

-1.64

acus

-1.57

SAS

-1.53

anski

-1.49

eh

-1.47

WW

-1.46

cair

-1.40

 mart

-1.40

POSITIVE LOGITS

etheless

1.76

ADRA

1.75

sites

1.49

dimension

1.46

Balance

1.45

rontal

1.44

direction

1.42

ridor

1.40

 usable

1.39

lace

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.