INDEX

Explanations

brief statements or notes on outcomes related to events or situations

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

0:0.15

1:0.10

2:0.10

3:0.05

4:0.04

5:0.02

6:0.09

7:0.11

8:0.03

9:0.03

10:0.18

11:0.04

Negative Logits

Nek

-3.52

 Kenyan

-2.82

 Devon

-2.81

Md

-2.65

cats

-2.61

 Scand

-2.61

 Perkins

-2.56

orks

-2.55

 Hare

-2.55

Fr

-2.52

POSITIVE LOGITS

TI

9.02

TI

6.38

SI

5.06

SI

5.01

TRI

3.93

 STEP

3.88

TAM

3.79

PI

3.75

Tang

3.67

CI

3.66

Activations Density 0.000%

brief statements or notes on outcomes related to events or situations

No Comments

No Known Activations