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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.09

3:0.08

4:0.09

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

gradation

-1.84

usable

-1.69

Reviewer

-1.65

ingu

-1.63

ensibly

-1.59

onomic

-1.55

ongyang

-1.52

formance

-1.52

 possession

-1.51

ioned

-1.50

POSITIVE LOGITS

Nap

1.61

icz

1.56

Mig

1.55

eni

1.52

talking

1.52

SPD

1.50

 Manz

1.50

mosp

1.50

 laughs

1.50

 Humph

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.