INDEX

Explanations

keywords related to a specific acronym or abbreviation, likely "SN"

oai_token-act-pair · gpt-3.5-turbo

references to specific "SN" codes or identifiers, possibly related to a series or classification system

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

tons

-0.75

nuts

-0.69

 Emir

-0.68

 Duchess

-0.67

mum

-0.67

 Emirates

-0.66

 Lama

-0.66

wings

-0.65

cens

-0.64

 mund

-0.64

POSITIVE LOGITS

OW

0.98

SN

0.93

MP

0.83

azer

0.79

OV

0.78

anu

0.77

oke

0.77

OOK

0.77

ASH

0.77

ATCH

0.77

Activations Density 0.040%

keywords related to a specific acronym or abbreviation, likely "SN"

references to specific "SN" codes or identifiers, possibly related to a series or classification system

No Comments

No Known Activations