INDEX

Explanations

references to communication or discussions that include questions and responses

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.07

1:0.12

2:0.11

3:0.07

4:0.06

5:0.06

6:0.08

7:0.10

8:0.09

9:0.07

10:0.06

11:0.05

Negative Logits

luster

-1.34

WAYS

-1.31

ModLoader

-1.13

inventoryQuantity

-1.12

ktop

-1.09

 territ

-1.08

 unification

-1.08

staking

-1.07

 arrang

-1.06

 membr

-1.04

POSITIVE LOGITS

装

1.28

1.27

arity

1.13

temp

1.12

版

1.12

ourke

1.11

icted

1.11

生

1.11

子

1.09

reference

1.08

Activations Density 0.003%

references to communication or discussions that include questions and responses

No Comments

No Known Activations