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

0:0.08

1:0.06

2:0.10

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

 constitu

-2.04

 instituted

-1.73

 ratified

-1.71

 implemented

-1.71

 reinstated

-1.64

 promul

-1.63

milo

-1.62

 fert

-1.61

 mathemat

-1.59

 instr

-1.59

POSITIVE LOGITS

skip

2.09

herry

1.70

 Column

1.70

column

1.67

mx

1.63

gallery

1.63

ogle

1.55

adata

1.54

ews

1.53

 previews

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.