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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.10

4:0.08

5:0.08

6:0.07

7:0.08

8:0.10

9:0.08

10:0.08

11:0.07

Negative Logits

inventoryQuantity

-1.69

ulner

-1.64

 compr

-1.58

oldown

-1.57

adesh

-1.56

 simulac

-1.53

iland

-1.52

ailability

-1.51

iffe

-1.48

alach

-1.47

POSITIVE LOGITS

Unit

1.70

Profile

1.66

amen

1.58

dragon

1.57

ometers

1.55

Nar

1.51

Variable

1.51

Sold

1.46

Phoenix

1.45

Studio

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.