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

1:0.07

2:0.07

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

ω

-2.02

osate

-1.97

icken

-1.96

��

-1.85

chwitz

-1.83

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

-1.78

gger

-1.78

trak

-1.78

bye

-1.76

raught

-1.75

POSITIVE LOGITS

 persist

1.82

 spor

1.73

 stagn

1.68

 poll

1.68

Lum

1.68

 showc

1.67

 slack

1.63

 langu

1.61

 misc

1.60

 prolific

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.