INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.09

5:0.07

6:0.09

7:0.07

8:0.06

9:0.08

10:0.07

11:0.08

Negative Logits

lear

-1.60

nig

-1.47

orth

-1.44

 glutamate

-1.35

 nitrogen

-1.34

-1.31

srf

-1.31

 detox

-1.31

erential

-1.28

Utt

-1.25

POSITIVE LOGITS

%"

1.55

 invocation

1.42

 solicitation

1.35

 Patreon

1.35

/,

1.34

 succeed

1.33

Forge

1.32

 Stard

1.32

 sponsoring

1.31

soDeliveryDate

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.