INDEX

Explanations

words and names related to popular figures or entities involved in legal contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.14

2:0.04

3:0.04

4:0.03

5:0.32

6:0.03

7:0.04

8:0.09

9:0.05

10:0.06

11:0.04

Negative Logits

closed

-2.05

atform

-1.94

lins

-1.88

access

-1.88

meric

-1.88

lished

-1.88

olls

-1.87

buck

-1.86

outheast

-1.85

other

-1.78

POSITIVE LOGITS

2.11

inj

1.98

 wrath

1.74

Mk

1.66

 Rebellion

1.65

 accus

1.61

 Unch

1.60

uberty

1.58

 lawsuit

1.56

 disobedience

1.54

Activations Density 0.000%

words and names related to popular figures or entities involved in legal contexts

No Comments

No Known Activations