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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.09

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

 Abilities

-1.77

 buds

-1.74

ム

-1.73

asks

-1.62

ufact

-1.60

xual

-1.60

し

-1.58

 accents

-1.54

Own

-1.52

 Engineers

-1.50

POSITIVE LOGITS

onite

2.46

odon

1.89

phia

1.89

milo

1.79

roxy

1.69

ramid

1.66

istani

1.65

otine

1.63

thouse

1.63

 Alto

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.