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

0:0.07

1:0.06

2:0.08

3:0.08

4:0.07

5:0.09

6:0.09

7:0.07

8:0.06

9:0.07

10:0.09

11:0.08

Negative Logits

]."

-1.79

 persecut

-1.47

 encamp

-1.45

 wasting

-1.42

 wandering

-1.42

 disappeared

-1.35

 drowning

-1.35

potion

-1.35

 massac

-1.35

 ruining

-1.33

POSITIVE LOGITS

anan

1.74

ctica

1.62

heid

1.55

illac

1.46

gary

1.44

yll

1.43

WAY

1.40

PG

1.39

andre

1.39

alach

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.