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

1:0.10

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

rette

-2.26

heim

-1.73

naire

-1.69

 paycheck

-1.68

ression

-1.64

olation

-1.61

amation

-1.58

 collegiate

-1.57

egu

-1.57

hell

-1.54

POSITIVE LOGITS

pse

1.71

natureconservancy

1.69

MH

1.61

 cautiously

1.58

 Cyrus

1.55

*/(

1.55

 裏�

1.53

Lex

1.52

 occurrences

1.51

KI

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.