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

0:0.09

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

 Surgery

-1.69

ongevity

-1.67

�

-1.65

 Conservation

-1.59

 Slightly

-1.59

 Veter

-1.58

 Written

-1.57

aternity

-1.55

 Penet

-1.55

 Forces

-1.53

POSITIVE LOGITS

ender

2.00

atto

1.84

relevant

1.76

:{

1.73

ess

1.70

arer

1.65

batch

1.60

changed

1.59

ourced

1.58

actionDate

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.