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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.08

2:0.09

3:0.06

4:0.08

5:0.07

6:0.11

7:0.10

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

 Display

-1.90

 Attacks

-1.90

 Events

-1.76

etc

-1.74

 Boxing

-1.71

 Cellular

-1.71

 Flags

-1.71

 Antar

-1.69

 Judgment

-1.67

 Defender

-1.66

POSITIVE LOGITS

pill

2.06

artisan

1.90

vier

1.79

Sov

1.75

reprene

1.75

esthes

1.72

romy

1.67

iom

1.64

onom

1.63

ashtra

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.