INDEX

Explanations

references to past statements or claims made by individuals

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

2:0.00

3:0.12

4:0.05

5:0.07

6:0.06

7:0.02

8:0.25

9:0.21

10:0.01

11:0.03

Negative Logits

agame

-1.88

 aggro

-1.83

 GOODMAN

-1.81

ynski

-1.79

$$$$

-1.78

 comparisons

-1.75

 positives

-1.75

uve

-1.74

 Skydragon

-1.74

matter

-1.72

POSITIVE LOGITS

 recently

2.03

 formerly

1.63

 cowork

1.62

 titled

1.62

 Theodore

1.56

 Gerald

1.55

Elm

1.54

 aborted

1.54

 granddaughter

1.53

 miscar

1.53

Activations Density 0.051%

references to past statements or claims made by individuals

No Comments

No Known Activations