INDEX

Explanations

phrases indicating increases, decreases, or changes in statistics and trends

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.02

1:0.04

2:0.08

3:0.06

4:0.02

5:0.06

6:0.09

7:0.16

8:0.07

9:0.07

10:0.07

11:0.22

Negative Logits

EStream

-1.16

params

-1.11

araoh

-1.09

 Oscars

-1.07

vet

-1.07

acea

-1.06

mp

-1.06

 mant

-1.06

itates

-1.04

anyahu

-1.03

POSITIVE LOGITS

Increase

1.24

chet

1.22

pread

1.19

USD

1.17

ensity

1.15

edly

1.14

 totaling

1.11

uits

1.11

imensional

1.10

pan

1.08

Activations Density 0.002%

phrases indicating increases, decreases, or changes in statistics and trends

No Comments

No Known Activations