INDEX

Explanations

mentions of events or significant occurrences in a timeline or 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_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.03

1:0.01

2:0.03

3:0.04

4:0.03

5:0.04

6:0.03

7:0.53

8:0.03

9:0.07

10:0.05

11:0.04

Negative Logits

EngineDebug

-1.51

EStreamFrame

-1.38

 camel

-1.38

◼

-1.37

kas

-1.37

�

-1.36

ioxide

-1.36

anol

-1.34

acus

-1.33

asus

-1.33

POSITIVE LOGITS

iture

1.99

itures

1.57

eatures

1.55

features

1.48

 grate

1.44

 memorial

1.44

iency

1.41

nces

1.41

FILE

1.40

minster

1.40

Activations Density 0.027%

mentions of events or significant occurrences in a timeline or narrative context

No Comments

No Known Activations