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

0:0.08

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.06

7:0.10

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

是

-1.77

 abstraction

-1.75

 emulation

-1.67

ESCO

-1.62

 immortality

-1.60

 UNESCO

-1.58

NEC

-1.58

 Creation

-1.58

 imagination

-1.54

 inflamm

-1.54

POSITIVE LOGITS

zinski

1.90

zb

1.86

gaard

1.83

bott

1.81

ventures

1.80

psons

1.79

bike

1.76

ipel

1.75

fake

1.71

bis

1.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.