INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 Yugoslav

-2.95

Kap

-2.94

SPI

-2.92

 Guatem

-2.85

Yug

-2.84

 Kamp

-2.74

 Morales

-2.72

TPP

-2.71

Zhu

-2.69

 Bravo

-2.69

POSITIVE LOGITS

 ordinarily

2.80

pite

2.71

STON

2.65

isson

2.65

ovember

2.62

Scope

2.54

auder

2.45

 Craw

2.41

ointment

2.40

iege

2.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.