INDEX

Explanations

words related to instructions, guidance, or procedural contexts

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.02

2:0.02

3:0.04

4:0.05

5:0.05

6:0.03

7:0.06

8:0.01

9:0.07

10:0.02

11:0.54

Negative Logits

 Flavoring

-2.38

Priv

-1.97

prem

-1.96

cest

-1.95

Rating

-1.95

Quant

-1.92

 Property

-1.92

things

-1.91

 Bris

-1.90

ック

-1.88

POSITIVE LOGITS

 directions

3.80

 footsteps

3.48

 steps

3.36

 path

3.25

 route

3.24

 paths

3.15

 trajectory

3.01

 trend

2.97

 traject

2.96

 playbook

2.92

Activations Density 0.074%

words related to instructions, guidance, or procedural contexts

No Comments

No Known Activations