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

1:0.06

2:0.08

3:0.09

4:0.07

5:0.09

6:0.07

7:0.07

8:0.09

9:0.09

10:0.07

11:0.07

Negative Logits

nai

-1.94

inventoryQuantity

-1.92

otte

-1.74

ription

-1.72

 contrace

-1.66

ebook

-1.62

ournals

-1.62

ulia

-1.60

orting

-1.60

 unequal

-1.59

POSITIVE LOGITS

 Helmet

1.72

 Known

1.71

 Intercept

1.71

 Mane

1.66

 Passenger

1.66

crew

1.66

 Breat

1.63

aundering

1.62

 Bloom

1.60

 Refuge

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.