INDEX

Explanations

instances of direct speech or quotes

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

0:0.06

1:0.07

2:0.06

3:0.07

4:0.10

5:0.06

6:0.08

7:0.15

8:0.07

9:0.08

10:0.08

11:0.06

Negative Logits

 civilisation

-1.92

 Grimm

-1.91

 Arkham

-1.84

 racket

-1.76

 Colony

-1.72

 settlement

-1.67

 nascent

-1.66

 mortals

-1.66

 partisans

-1.65

 Citizens

-1.63

POSITIVE LOGITS

netflix

2.10

ussen

2.01

tumblr

1.95

umbn

1.94

items

1.91

utz

1.86

iatric

1.81

dl

1.80

reau

1.79

signed

1.79

Activations Density 0.000%

instances of direct speech or quotes

No Comments

No Known Activations