INDEX

Explanations

references to specific locations or objects within a narrative context

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

0:0.01

1:0.02

2:0.12

3:0.25

4:0.02

5:0.04

6:0.05

7:0.08

8:0.13

9:0.06

10:0.08

11:0.09

Negative Logits

ict

-1.24

aciously

-1.04

 boycot

-1.03

trak

-1.02

jen

-1.01

isoft

-1.01

ept

-0.99

 adjunct

-0.98

educ

-0.97

iatric

-0.97

POSITIVE LOGITS

 rooft

1.36

 territory

1.12

 canvas

1.10

 lines

1.08

 dots

1.08

 boundaries

1.07

 landscape

1.05

 landscapes

1.05

rome

1.05

 wires

1.04

Activations Density 0.015%

references to specific locations or objects within a narrative context

No Comments

No Known Activations