INDEX

Explanations

terms related to financial misconduct or fraud

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

0:0.10

1:0.02

2:0.12

3:0.13

4:0.07

5:0.23

6:0.03

7:0.12

8:0.03

9:0.03

10:0.04

11:0.03

Negative Logits

 behavi

-1.96

 coward

-1.93

abiding

-1.90

 stupidity

-1.79

ottesville

-1.74

 bullies

-1.74

 bully

-1.74

EStream

-1.72

============

-1.72

enment

-1.71

POSITIVE LOGITS

 canceled

1.68

 Hawaiian

1.63

Mau

1.56

 Haitian

1.55

 cancellation

1.50

 refunds

1.50

raft

1.48

 awarding

1.47

 applications

1.46

 Aval

1.44

Activations Density 1.006%

terms related to financial misconduct or fraud

No Comments

No Known Activations