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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Axis

-1.70

 Bagg

-1.69

ּ

-1.69

aves

-1.68

 Gest

-1.62

 salute

-1.61

 allele

-1.61

 Anders

-1.59

ROR

-1.56

ドラゴン

-1.55

POSITIVE LOGITS

aii

1.89

bitious

1.76

 catching

1.74

grad

1.67

 inund

1.66

 dilig

1.62

weet

1.62

mercial

1.61

ombo

1.61

 spreading

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.