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

0:0.06

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.10

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

 helic

-2.01

Rh

-1.83

ner

-1.69

XXX

-1.61

 Tight

-1.57

 Tyrann

-1.56

 Vegan

-1.53

gravity

-1.52

fortunately

-1.52

Ib

-1.50

POSITIVE LOGITS

Reviewer

1.86

enance

1.71

vertisement

1.66

nation

1.64

'>

1.60

 Appearance

1.58

join

1.55

 berth

1.53

comings

1.51

*/(

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.