INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.08

1:0.09

2:0.07

3:0.08

4:0.06

5:0.09

6:0.10

7:0.09

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

 whats

-1.98

Closure

-1.96

 thats

-1.96

cember

-1.91

nt

-1.91

luaj

-1.89

bors

-1.89

RW

-1.88

-1.86

aka

-1.84

POSITIVE LOGITS

 Hegel

2.11

cius

2.06

ograph

2.05

 Classical

2.02

 Ethiop

1.86

 Mobil

1.86

 Gallup

1.85

eton

1.79

 Invention

1.77

ographs

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.