INDEX

Explanations

statements asserting facts or opinions about situations or subjects

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

0:0.01

1:0.05

2:0.07

3:0.03

4:0.02

5:0.04

6:0.08

7:0.06

8:0.07

9:0.11

10:0.06

11:0.35

Negative Logits

cellaneous

-1.34

ourn

-1.29

)"

-1.20

lication

-1.20

along

-1.20

Exit

-1.19

ews

-1.18

 plun

-1.10

endi

-1.10

ienne

-1.10

POSITIVE LOGITS

 deceive

1.25

avorite

1.17

 contradicted

1.13

 cheated

1.13

 plagiar

1.10

 サーティワン

1.10

incerity

1.10

 lied

1.09

 Percent

1.09

 Hoff

1.08

Activations Density 0.038%

statements asserting facts or opinions about situations or subjects

No Comments

No Known Activations