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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.09

5:0.07

6:0.09

7:0.09

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

 blot

-1.79

rored

-1.77

 mirrored

-1.66

 frown

-1.61

 chromosomes

-1.60

 constitu

-1.56

 stride

-1.55

 capacitor

-1.51

 ripple

-1.51

Timeout

-1.50

POSITIVE LOGITS

ngth

1.77

glers

1.70

foo

1.63

 Tours

1.63

["

1.60

wagen

1.59

ylum

1.58

slaught

1.56

reb

1.55

hower

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.