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

0:0.07

1:0.07

2:0.09

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.10

9:0.09

10:0.06

11:0.07

Negative Logits

arma

-2.02

roma

-1.91

acons

-1.89

ucks

-1.84

itte

-1.83

acon

-1.82

itness

-1.81

 pione

-1.80

iral

-1.79

okes

-1.79

POSITIVE LOGITS

 unsupported

1.90

creen

1.70

 Genie

1.69

 Glover

1.66

MGM

1.66

 unavailable

1.63

Kyl

1.62

 Murdoch

1.61

TBA

1.61

 Fifa

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.