INDEX

Explanations

No Explanations Found

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.05

2:0.08

3:0.07

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

 droid

-1.82

cycles

-1.79

RC

-1.73

raq

-1.72

mint

-1.69

rpm

-1.64

CBC

-1.56

MO

-1.55

rose

-1.55

bike

-1.53

POSITIVE LOGITS

erent

1.82

 Tanz

1.71

 Gould

1.70

otin

1.55

 Nanto

1.53

 appell

1.49

 Ibid

1.46

 Ples

1.46

 Opportun

1.45

}}}

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.