INDEX

Explanations

questions about identity and self-perception

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_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

0:0.02

1:0.02

2:0.09

3:0.08

4:0.20

5:0.03

6:0.03

7:0.23

8:0.08

9:0.05

10:0.06

11:0.05

Negative Logits

etheless

-1.96

esters

-1.80

adr

-1.70

cit

-1.68

asury

-1.68

abase

-1.68

avery

-1.68

ravel

-1.67

vati

-1.61

ItemTracker

-1.61

POSITIVE LOGITS

 advis

1.97

 aloud

1.91

 faults

1.74

 deeds

1.68

 names

1.64

 ______

1.63

 hazards

1.62

 kisses

1.60

 subscript

1.59

 secrets

1.55

Activations Density 0.016%

questions about identity and self-perception

No Comments

No Known Activations