INDEX

Explanations

expressions related to actions and decision-making

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

0:0.35

1:0.02

2:0.23

3:0.07

4:0.02

5:0.04

6:0.02

7:0.04

8:0.03

9:0.03

10:0.07

11:0.02

Negative Logits

 Univ

-2.71

 breakfast

-2.70

 bride

-2.66

reader

-2.63

 fonts

-2.61

font

-2.53

 curly

-2.49

 hosting

-2.46

 columnist

-2.45

 programming

-2.45

POSITIVE LOGITS

 ACTIONS

4.18

 Actions

3.96

 actions

3.90

 action

3.62

actions

3.58

action

3.39

ACTION

3.21

Action

3.20

 retaliation

3.08

 inaction

3.07

Activations Density 0.028%

expressions related to actions and decision-making

No Comments

No Known Activations