INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.09

2:0.07

3:0.06

4:0.09

5:0.09

6:0.09

7:0.08

8:0.06

9:0.07

10:0.06

11:0.10

Negative Logits

wolves

-1.90

ieth

-1.74

,[

-1.72

(#

-1.70

din

-1.68

Tree

-1.65

ope

-1.63

ocene

-1.63

(&

-1.61

osity

-1.59

POSITIVE LOGITS

 blackmail

1.72

 compliant

1.63

Ire

1.60

 supervision

1.56

compl

1.53

uphem

1.48

 confidentiality

1.46

 subcontract

1.44

xiety

1.43

gag

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.