INDEX

Explanations

phrases related to structures and buildings

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.10

1:0.01

2:0.10

3:0.17

4:0.05

5:0.31

6:0.03

7:0.05

8:0.05

9:0.02

10:0.03

11:0.02

Negative Logits

 closures

-2.52

 fences

-2.19

 landowners

-2.18

 tresp

-2.11

 paddle

-2.11

 landsc

-2.09

 signage

-2.08

 trespass

-2.08

 locations

-2.04

 closure

-2.02

POSITIVE LOGITS

 Intelligence

1.83

 Papers

1.83

 Psychiatry

1.75

utics

1.74

Psy

1.73

Psy

1.72

 Psycho

1.71

 Psychological

1.70

raft

1.69

 Viet

1.66

Activations Density 1.412%

phrases related to structures and buildings

No Comments

No Known Activations