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

3:0.09

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

hower

-2.15

heastern

-2.06

leneck

-1.87

ieved

-1.86

inement

-1.82

oit

-1.81

resist

-1.80

ucket

-1.75

plet

-1.75

ilus

-1.74

POSITIVE LOGITS

ゴン

2.12

 endorsements

1.93

 Commentary

1.92

 announcer

1.84

姫

1.84

 quotations

1.81

 Rookie

1.72

 Editor

1.71

 advertisements

1.70

 Minutes

1.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.