INDEX

Explanations

clues and indicators related to evidence or information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.07

3:0.07

4:0.13

5:0.02

6:0.04

7:0.40

8:0.02

9:0.02

10:0.09

11:0.06

Negative Logits

ITED

-1.85

ーク

-1.81

ylum

-1.68

 subsid

-1.59

BuyableInstoreAndOnline

-1.56

ा

-1.54

Rated

-1.51

Duration

-1.46

ーティ

-1.45

Rating

-1.43

POSITIVE LOGITS

 whereabouts

1.83

 unsus

1.72

 clues

1.64

 mysteries

1.61

 spotting

1.61

 Awakening

1.55

ommel

1.54

 Hidden

1.53

 decipher

1.52

 sightings

1.51

Activations Density 0.002%

clues and indicators related to evidence or information

No Comments

No Known Activations