INDEX

Explanations

conjunctions and phrases indicating connection or continuity

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

0:0.19

1:0.02

2:0.15

3:0.04

4:0.08

5:0.05

6:0.03

7:0.03

8:0.18

9:0.05

10:0.05

11:0.07

Negative Logits

luent

-1.58

icient

-1.56

tic

-1.56

nel

-1.47

ocre

-1.35

theless

-1.35

uese

-1.34

astically

-1.33

edi

-1.33

iuses

-1.32

POSITIVE LOGITS

��

1.97

etc

1.80

thumbnails

1.54

etc

1.52

AppData

1.51

 timelines

1.47

 hers

1.45

quished

1.44

Together

1.42

 theirs

1.42

Activations Density 0.015%

conjunctions and phrases indicating connection or continuity

No Comments

No Known Activations