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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.07

3:0.10

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

inventoryQuantity

-2.44

itbart

-2.25

 Breitbart

-1.90

aptic

-1.87

omers

-1.85

nesday

-1.80

argon

-1.79

 GamerGate

-1.77

chwitz

-1.77

alions

-1.73

POSITIVE LOGITS

Dj

1.85

 Amen

1.78

�

1.72

Unique

1.72

 Pref

1.72

 Places

1.72

�

1.71

三

1.69

 Overt

1.68

 Judges

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.