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

2:0.09

3:0.09

4:0.06

5:0.07

6:0.07

7:0.10

8:0.07

9:0.08

10:0.10

11:0.08

Negative Logits

 answering

-1.76

 insight

-1.64

 label

-1.63

 compress

-1.63

 compressor

-1.60

 answer

-1.59

 enlight

-1.57

 selection

-1.55

 discl

-1.55

 foundation

-1.54

POSITIVE LOGITS

adj

2.03

--------------------------------------------------------

1.97

女

1.96

imester

1.86

////////////////////////////////

1.86

oat

1.86

Rated

1.84

Ey

1.82

Developer

1.79

ーティ

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.