INDEX

Explanations

phrases indicating physical actions or movement

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

0:0.09

1:0.05

2:0.10

3:0.13

4:0.08

5:0.10

6:0.07

7:0.11

8:0.06

9:0.06

10:0.06

11:0.04

Negative Logits

 patrons

-2.97

 customers

-2.84

 visitors

-2.82

goers

-2.67

 passers

-2.63

 doors

-2.54

 visitor

-2.54

 customer

-2.54

 employees

-2.53

 service

-2.48

POSITIVE LOGITS

 abolished

2.87

ieties

2.74

 histor

2.67

afort

2.63

RFC

2.61

ortium

2.59

 exoner

2.52

版

2.52

OPA

2.52

cussion

2.45

Activations Density 0.000%

phrases indicating physical actions or movement

No Comments

No Known Activations