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

0:0.12

1:0.09

2:0.09

3:0.07

4:0.07

5:0.06

6:0.09

7:0.05

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 Talking

-1.55

 Hockey

-1.53

Seg

-1.53

 Block

-1.51

,[

-1.50

 derog

-1.49

Footnote

-1.48

ohn

-1.43

Sty

-1.40

 Fiat

-1.39

POSITIVE LOGITS

ocrates

1.77

WARE

1.73

ashtra

1.63

 STATS

1.57

 trig

1.52

 spir

1.52

 outnumbered

1.51

erial

1.49

ktop

1.48

kid

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.