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

2:0.10

3:0.08

4:0.08

5:0.06

6:0.09

7:0.08

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

brance

-1.98

/$

-1.94

endif

-1.67

 equivalents

-1.66

MX

-1.58

MX

-1.58

fml

-1.56

payer

-1.54

 Chimera

-1.54

CF

-1.53

POSITIVE LOGITS

pmwiki

1.81

Story

1.73

 voices

1.72

CLASSIFIED

1.70

Plot

1.68

OHN

1.67

hatt

1.65

onso

1.64

 incorpor

1.59

Crime

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.