INDEX

Explanations

elements related to translation and data representation

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

0:0.04

1:0.02

2:0.05

3:0.06

4:0.35

5:0.05

6:0.04

7:0.13

8:0.03

9:0.05

10:0.07

11:0.06

Negative Logits

adelphia

-1.64

quished

-1.59

 Shrine

-1.56

payers

-1.56

mbuds

-1.54

ubis

-1.53

racuse

-1.51

etheless

-1.47

lesh

-1.47

maxwell

-1.46

POSITIVE LOGITS

 cues

1.58

cue

1.55

 sentences

1.51

 stimulus

1.49

 onto

1.44

 into

1.42

 advances

1.41

 impulses

1.41

 nonsense

1.41

 tragedies

1.41

Activations Density 0.001%

elements related to translation and data representation

No Comments

No Known Activations