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

0:0.07

1:0.09

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

icans

-2.12

SELECT

-2.01

izens

-1.96

 BALL

-1.95

atro

-1.91

ordes

-1.85

flies

-1.78

CRE

-1.76

anches

-1.74

boys

-1.73

POSITIVE LOGITS

 curfew

1.83

 permissible

1.81

 deductible

1.66

 cradle

1.65

 handc

1.64

··

1.64

utral

1.64

 comma

1.62

 driveway

1.61

 dentist

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.