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

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 experien

-1.79

iott

-1.67

 elig

-1.65

 Sagan

-1.63

 anecd

-1.59

 undergraduate

-1.54

 undergrad

-1.51

 guiActiveUn

-1.50

*/(

-1.49

 accus

-1.49

POSITIVE LOGITS

endif

1.82

alias

1.82

ridges

1.78

ulture

1.78

translation

1.77

rust

1.72

wheel

1.72

人

1.69

uria

1.69

look

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.