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

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.11

9:0.07

10:0.08

11:0.08

Negative Logits

 Rubin

-1.71

 metaphors

-1.70

 Yiannopoulos

-1.66

 Bian

-1.66

 Engel

-1.64

 Dalai

-1.63

ESL

-1.63

paces

-1.62

utical

-1.58

Seg

-1.57

POSITIVE LOGITS

 unaccount

1.93

 mainland

1.81

umably

1.75

irm

1.74

arently

1.70

 unspecified

1.68

irmed

1.67

 repaired

1.66

 unidentified

1.64

 offshore

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.