INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.09

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

pty

-3.13

rito

-2.96

ahon

-2.89

Rh

-2.89

atto

-2.85

rique

-2.73

breeding

-2.71

rh

-2.65

ications

-2.62

-2.57

POSITIVE LOGITS

 APPLIC

2.92

 Gale

2.68

ES

2.64

Yel

2.64

 Actions

2.64

 sqor

2.57

JPM

2.56

 Levy

2.53

 Berk

2.50

 Greene

2.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.