INDEX

Explanations

names of individuals, potentially in a news or information context, with a focus on surnames

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and surnames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 carbohyd

-0.72

 millenn

-0.70

Þ

-0.70

ß

-0.68

 tradem

-0.68

akespe

-0.64

pse

-0.63

PDATE

-0.62

 favourable

-0.62

acebook

-0.60

POSITIVE LOGITS

lein

0.93

berger

0.91

stown

0.89

ansky

0.88

mann

0.86

stein

0.86

meyer

0.81

 Associates

0.79

 County

0.79

meier

0.77

Activations Density 0.381%

names of individuals, potentially in a news or information context, with a focus on surnames

proper nouns, particularly names and surnames

No Comments

No Known Activations