INDEX

Explanations

occurrences of phrases that denote or represent concepts of identity or belonging

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.03

2:0.12

3:0.09

4:0.12

5:0.04

6:0.19

7:0.02

8:0.09

9:0.11

10:0.08

11:0.04

Negative Logits

 machinery

-1.57

 perpend

-1.51

Klu

-1.48

��

-1.42

 simulac

-1.40

 inappropriately

-1.37

YPG

-1.37

Oy

-1.37

 culprit

-1.37

 Palest

-1.36

POSITIVE LOGITS

bern

2.01

reon

1.75

winter

1.61

urrection

1.56

rue

1.56

arten

1.55

Reviewer

1.51

ictionary

1.51

ilan

1.51

endor

1.48

Activations Density 0.052%

occurrences of phrases that denote or represent concepts of identity or belonging

No Comments

No Known Activations