INDEX

Explanations

statements related to economic metrics and performance rankings

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.10

1:0.09

2:0.06

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

IGHTS

-3.15

hod

-2.78

RECT

-2.78

IRT

-2.61

ONY

-2.60

FIG

-2.59

Psy

-2.58

IVES

-2.56

FAC

-2.55

Priv

-2.54

POSITIVE LOGITS

 Carlo

2.93

esson

2.79

amo

2.78

 tyre

2.69

ospels

2.68

erva

2.62

 Lester

2.59

odiac

2.56

ivari

2.54

 Worcester

2.51

Activations Density 0.000%

statements related to economic metrics and performance rankings

No Comments

No Known Activations