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

1:0.09

2:0.08

3:0.07

4:0.07

5:0.08

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

paio

-2.84

ESA

-2.66

 rover

-2.64

phabet

-2.59

HW

-2.57

lehem

-2.56

-2.54

ractor

-2.53

 Rivals

-2.49

 Traff

-2.47

POSITIVE LOGITS

ieties

2.66

 Bour

2.52

 conventions

2.52

 Fever

2.50

lore

2.40

Du

2.39

icism

2.35

 Seasons

2.33

 Garr

2.32

chy

2.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.