INDEX

Explanations

phrases indicating criteria or characteristics to look for in a person or thing

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.02

1:0.01

2:0.08

3:0.07

4:0.11

5:0.04

6:0.02

7:0.32

8:0.06

9:0.04

10:0.11

11:0.07

Negative Logits

 deaf

-1.66

ouched

-1.56

anches

-1.56

 brothers

-1.55

ú

-1.55

 pupp

-1.54

bucks

-1.54

jad

-1.50

azeera

-1.47

ł

-1.46

POSITIVE LOGITS

 Defin

1.79

 Definition

1.74

 Excellence

1.72

 explan

1.68

 Identification

1.63

 Establishment

1.58

 Ideally

1.56

の魔

1.55

 Recommended

1.55

 appraisal

1.52

Activations Density 0.001%

phrases indicating criteria or characteristics to look for in a person or thing

No Comments

No Known Activations