INDEX

Explanations

formal permissions and legal requirements concerning actions, decisions, or processes

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

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

0:0.01

1:0.02

2:0.16

3:0.30

4:0.10

5:0.03

6:0.03

7:0.06

8:0.05

9:0.04

10:0.10

11:0.05

Negative Logits

avery

-1.70

acer

-1.69

emale

-1.64

hens

-1.63

ⓘ

-1.59

udos

-1.55

aughter

-1.54

comings

-1.53

achine

-1.52

oled

-1.50

POSITIVE LOGITS

or

1.79

 otherwise

1.75

 sufficiently

1.74

 sufficient

1.74

 elsewhere

1.64

 somewhere

1.60

 somehow

1.59

 enough

1.55

 reasonably

1.55

 lapse

1.51

Activations Density 0.026%

formal permissions and legal requirements concerning actions, decisions, or processes

No Comments

No Known Activations