INDEX

Explanations

references to hobbies and leisure activities

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

0:0.03

1:0.01

2:0.05

3:0.05

4:0.10

5:0.04

6:0.04

7:0.36

8:0.03

9:0.03

10:0.12

11:0.08

Negative Logits

 decisive

-1.63

 arguments

-1.53

 outnumbered

-1.45

 infall

-1.45

 proposition

-1.43

 attest

-1.43

soDeliveryDate

-1.43

 victories

-1.42

 weaker

-1.42

 claimant

-1.42

POSITIVE LOGITS

hig

1.88

 curiosity

1.71

 Painting

1.65

Category

1.61

Brow

1.59

 Photography

1.58

Cra

1.50

Debug

1.47

Pain

1.47

hunt

1.46

Activations Density 0.001%

references to hobbies and leisure activities

No Comments

No Known Activations