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

1:0.08

2:0.10

3:0.07

4:0.09

5:0.07

6:0.09

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

ovember

-2.15

assador

-1.74

clusively

-1.73

edIn

-1.72

osate

-1.71

-1.68

enough

-1.68

mouth

-1.64

 Booster

-1.63

魔

-1.61

POSITIVE LOGITS

ield

1.84

 String

1.80

Elm

1.64

pad

1.61

ⓘ

1.61

 cipher

1.51

 Mutant

1.50

 Byte

1.49

sein

1.49

 Collins

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.