INDEX

Explanations

quotation marks and related structure in the text

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

0:0.10

1:0.10

2:0.05

3:0.05

4:0.09

5:0.04

6:0.13

7:0.08

8:0.06

9:0.05

10:0.10

11:0.10

Negative Logits

emort

-2.46

cius

-2.44

 Corps

-2.41

apeake

-2.41

ersive

-2.39

 Overse

-2.38

 Voices

-2.37

 mans

-2.36

 Audit

-2.35

 Thornton

-2.31

POSITIVE LOGITS

brand

3.32

price

2.97

Store

2.85

priced

2.79

�

2.77

Catalog

2.76

 Barg

2.75

shop

2.72

 bidder

2.67

Price

2.63

Activations Density 0.000%

quotation marks and related structure in the text

No Comments

No Known Activations