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

1:0.06

2:0.08

3:0.07

4:0.09

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

pez

-1.91

eger

-1.71

capt

-1.62

found

-1.53

rys

-1.52

clip

-1.51

gotten

-1.50

ppings

-1.48

burning

-1.45

Ort

-1.44

POSITIVE LOGITS

Dialogue

1.81

)=(

1.80

zona

1.69

akura

1.68

 conformity

1.68

 Decision

1.66

Relations

1.62

 Flavoring

1.60

 behavi

1.59

 Commentary

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.