INDEX

Explanations

symbols or formatting elements 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

0:0.08

1:0.08

2:0.06

3:0.07

4:0.08

5:0.10

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

Ov

-2.83

Volume

-2.83

 Greenwich

-2.81

avascript

-2.69

 resemb

-2.62

MUS

-2.60

rodu

-2.59

ersive

-2.59

 ensemble

-2.59

Lat

-2.54

POSITIVE LOGITS

rick

2.85

mberg

2.83

Doc

2.72

 Griff

2.67

atoon

2.63

 Drill

2.62

zinski

2.61

/>

2.61

"/>

2.60

 Podesta

2.56

Activations Density 0.000%

symbols or formatting elements in the text

No Comments

No Known Activations