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

3:0.08

4:0.06

5:0.08

6:0.06

7:0.07

8:0.08

9:0.09

10:0.10

11:0.08

Negative Logits

 elect

-1.72

��

-1.57

 shine

-1.54

 complexion

-1.54

 wiser

-1.53

 Presidency

-1.53

 compromises

-1.52

 Dove

-1.52

 aspir

-1.51

 racially

-1.51

POSITIVE LOGITS

staking

2.02

nown

1.88

Tokens

1.76

████

1.71

*/(

1.71

inventoryQuantity

1.69

SpaceEngineers

1.68

DragonMagazine

1.67

sie

1.66

adj

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.