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

1:0.11

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

VERTISEMENT

-1.88

 Myanmar

-1.75

 Florence

-1.73

 CrossRef

-1.72

»

-1.69

?」

-1.65

}"

-1.62

interrupted

-1.55

?]

-1.55

 Leilan

-1.54

POSITIVE LOGITS

 subpoen

1.89

anski

1.64

andan

1.57

collect

1.56

HOU

1.55

hibit

1.53

ハ

1.53

tro

1.53

kan

1.49

roph

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.