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

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

5:0.09

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

 Leilan

-1.88

 GOODMAN

-1.83

uther

-1.75

orers

-1.60

-1.57

pha

-1.57

 Glob

-1.55

acion

-1.54

ivity

-1.52

anguages

-1.51

POSITIVE LOGITS

ofi

1.76

helm

1.73

Bos

1.67

sbm

1.66

Rus

1.66

lopp

1.62

 withd

1.60

Wars

1.59

sic

1.55

bo

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.