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

Head Attr Weights

0:0.09

1:0.08

2:0.09

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.06

11:0.08

Negative Logits

 caution

-1.80

natureconservancy

-1.73

\\\\\\\\

-1.71

pmwiki

-1.69

 spoiler

-1.66

 advis

-1.57

 politic

-1.57

 panic

-1.56

 ripple

-1.55

版

-1.53

POSITIVE LOGITS

/$

1.97

eligible

1.80

arthed

1.72

raped

1.69

aught

1.66

hemoth

1.65

classified

1.65

hips

1.64

ryu

1.64

ensis

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.