INDEX

Explanations

names mentioned, presumably with a special focus on usernames or handles

oai_token-act-pair · gpt-3.5-turbo

references to specific names and brands within the content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ske

-0.86

 handic

-0.85

SAP

-0.82

 Carib

-0.81

Haz

-0.80

Emb

-0.78

Tib

-0.77

HRC

-0.76

 medic

-0.75

 Scouting

-0.74

POSITIVE LOGITS

ons

1.52

oni

1.44

onian

1.44

ON

1.42

on

1.41

onal

1.37

onia

1.34

onic

1.33

ony

1.31

onis

1.30

Activations Density 0.192%

names mentioned, presumably with a special focus on usernames or handles

references to specific names and brands within the content

No Comments

No Known Activations