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

0:0.09

1:0.06

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

lished

-1.98

�

-1.92

lishes

-1.81

Tes

-1.80

GBT

-1.76

BIP

-1.67

Hope

-1.65

GMT

-1.64

RFC

-1.62

miah

-1.59

POSITIVE LOGITS

 occupations

1.89

 surprises

1.77

 matters

1.65

 manifests

1.62

 vaccinations

1.60

education

1.60

 Activities

1.55

 experiences

1.55

 waivers

1.54

 Cosponsors

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.