INDEX

Explanations

locations or places, especially ones with 'Long' in the name

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Long."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 comprom

-0.63

ADVERTISEMENT

-0.62

natureconservancy

-0.62

iances

-0.61

utical

-0.60

 Flavoring

-0.60

ADRA

-0.59

ICAN

-0.59

 Compass

-0.59

IRO

-0.58

POSITIVE LOGITS

itudinal

1.43

itud

1.25

itude

1.08

sword

1.04

itudes

0.96

reads

0.96

est

0.95

mire

0.94

shore

0.94

enhagen

0.94

Activations Density 0.035%

locations or places, especially ones with 'Long' in the name

mentions of the term "Long."

No Comments

No Known Activations